--- title: "Senior Product Engineer - AI Native at DiliTrust – VueJobs" canonical_url: "https://vuejobs.com/jobs/dilitrust-senior-product-engineer-ai-native" meta: "og:image": "https://vuejobs.com/_og/d/c_PostDetail%2Ctitle_Senior%2BProduct%2BEngineer%2B-%2BAI%2BNative%2Cheadline_DiliTrust%2Cimage_~aHR0cHM6Ly9hc3NldHMuam9iYmIuaW8vbG9nb3MvMDFrZTBoMnR3ZDY5N24yOXpqMGpnZndiOGNfMTc2NzM5Njk2Mi5wbmc%2Cp_Ii9qb2JzL2RpbGl0cnVzdC1zZW5pb3ItcHJvZHVjdC1lbmdpbmVlci1haS1uYXRpdmUi%2Cs_5LdBxgb5dWJ8nvJC.png" "og:image:height": "630" "og:image:type": image/png "og:image:width": "1200" "og:title": "Senior Product Engineer - AI Native at DiliTrust – VueJobs" "twitter:image": "https://vuejobs.com/_og/d/c_PostDetail%2Ctitle_Senior%2BProduct%2BEngineer%2B-%2BAI%2BNative%2Cheadline_DiliTrust%2Cimage_~aHR0cHM6Ly9hc3NldHMuam9iYmIuaW8vbG9nb3MvMDFrZTBoMnR3ZDY5N24yOXpqMGpnZndiOGNfMTc2NzM5Njk2Mi5wbmc%2Cp_Ii9qb2JzL2RpbGl0cnVzdC1zZW5pb3ItcHJvZHVjdC1lbmdpbmVlci1haS1uYXRpdmUi%2Cs_5LdBxgb5dWJ8nvJC.png" --- > Index of every page on this site: [llms.txt](https://vuejobs.com/llms.txt) # **Senior Product Engineer - AI Native** DiliTrust Vue-plus **Backend** ![Flag of France](https://hatscripts.github.io/circle-flags/flags/fr.svg) Paris, Francehybridfull-timesenior1 month ago [**Apply Now **](https://jobs.lever.co/dilitrust/d92d3355-e6c5-4949-9621-2506543e81a9?ref=vuejobs.com) --- ### Ready to be part of the Legal Tech revolution? **Vision:** As a leading software-as-a-service (SaaS) provider, DiliTrust is a global company dedicated to offering an integrated suite of legal and governance products. Our vision is to digitize legal departments worldwide. With an annual growth rate of over 40% since 2020, our ambition is to become the world's leading Legal Tech company, aiming for a valuation exceeding $1 billion by 2026. **Our Impact:** From generating General Meeting reports to leveraging AI-assisted contract lifecycle management, our teams in our 8 offices across France, the US, Mexico, MEA, Germany, Spain, Italy, and Canada are the driving force behind our global success. We proudly support 2,400 customers in 64 countries, with 80% of our clientele comprising listed companies in major markets such as Europe, North America, and the Middle East. **Our Recognition:** DiliTrust has been at the forefront of Legal Tech innovation, being the first Legal Tech with AI features since 2022. The company is renowned for providing a positive and entrepreneurial work environment. We are honored to have received the "Happy at Work" and "Tech at Work" labels every year since 2019. ### The Role: Lini is DiliTrust's proprietary AI engine, powering Ask Lini, Risk Detector, Document Summarization, Minute Generation, and every AI capability across the suite. We are building a dedicated squad around it and are looking for a strong Software / Product Engineer, with a focus our platform architecture, to help us bring it to the next level. As a Software Engineer work at the intersection of AI, product, and engineering. You will contribute to building, improving, and scaling the features that make Lini a reliable and powerful AI layer across the entire DiliTrust suite. We are looking for an engineer who writes clean, production-ready code and is comfortable taking ownership of features end-to-end, from technical design to deployment. We also care about how you think about AI: whether you bring genuine curiosity to the product, and whether you can translate a model capability into a great user experience. --- ## Missions - **Write specifications as the durable asset of the project.** Executable acceptance criteria, and — crucially — the non-functional requirements that specs almost never carry: data classification, endpoint × role authorization matrix, volumetry assumptions, latency and throughput budgets. These are the requirements whose later correction is superlinear, so they get decided before generation, not after. - **Freeze the contracts before any fan-out.** API schemas, types, module boundaries, invariants. Agents do not negotiate an interface in the hallway: each will make a plausible and incompatible assumption, discovered at integration. - **Pilot coding agents with a tight brief and a bounded context** — narrow tasks, defined input and output artifacts, explicit stop conditions and budgets, full traceability of what produced each change. - **Keep producer and verifier separate.** You do not sign off alone on generation you piloted, and you act as independent verifier on your peers' slices — with an adversarial brief ("find what breaks against this spec"), never "confirm this looks fine". - **Build the asymmetric gates that make the slice safe at volume** — expensive to satisfy, cheap to check: property tests, contract tests, query-count and allocation budgets, execution-plan checks, policy-as-code, backward-compatibility proofs. Written *before* the implementation exists, so the agent closes the feedback loop itself without consuming human attention. - **Use code reading as a calibration instrument, not as a gate.** Sample deliberately, by risk zone, to measure the real defect rate of the generator-plus-gates pair and to keep the team's mental model of its own system alive. - **Keep work-in-progress low.** Capped PR size, thin vertical slices, trunk-based with very short branches, feature flags over long-lived branches, CI as the agent's first task rather than its last. More features in flight does not mean faster delivery when the bottleneck is verification. - **Design for blast radius.** Reversibility, progressive delivery, structured logs, traces, metrics and instrumentation generated as a matter of course. On many paths, detecting in five minutes beats three days of review that prevents nothing. --- ## Requirements **Being based in France with full working rights.** **Fluent in French and English.** **Experience & Seniority:** - 8+ years of professional software engineering experience, with a significant portion spent building and operating B2B SaaS platforms in production - Proven ownership of features across their full lifecycle — design, delivery, iteration, maintenance — on long-lived, multi-year products - Strong background in complex, scalable web architectures, including real modularity: you have seen where coupling stops parallel work dead **AI-Native Practice:** - Demonstrated, sustained use of coding agents in production work — not autocomplete, but delegated implementation with review and accountability - A concrete, articulated view of where generated code fails: correlated defects rather than idiosyncratic ones, uniform surface quality that destroys the usual "look here" review signals, plausibility with no author to interrogate - Comfort being accountable for code you did not author, and the discipline to refuse a change you cannot explain **Verification & Quality:** - Real fluency in property-based testing, contract testing, and deriving tests from the specification rather than from the code - Test-data strategy, including maintaining a volumetrically representative dataset as part of the verification apparatus — not a nice-to-have - Instinct for the difference between a rigorous check and a *scalable* one: does the cost of checking grow with the volume produced? **Security & Performance (non-negotiable on this role):** - Authorization modelling in multi-tenant systems, and why declarative, centrally enforced authorization beats reviewing each endpoint. Generated code reliably checks *who* you are and regularly forgets *whether you are allowed* - Awareness of the attack surface specific to an agent-assisted pipeline: prompt injection through ticket descriptions, code comments and dependency READMEs; supply-chain risk on hallucinated package names; least privilege for non-human identities; and the most frequent risk of all — production data or proprietary code leaking into the development loop - Performance as a measured number rather than a code-reading opinion: query budgets per HTTP request, N+1, unbounded result sets, missing indexes on new query paths, network calls in loops, execution-plan review. These are invisible at test-data scale and expensive in production **Product & Team Collaboration:** - Excellent written communication — specification writing is now a core engineering skill on this role, not documentation overhead - Extensive experience working directly with product managers, designers and stakeholders in a product-oriented setup - Strong sense of ownership and sound judgment on risk: what to build, what not to build, what residual risk is acceptable and why **Education:** - Master's degree in Engineering or equivalent practical experience in senior SaaS environments --- ## What this role is not We would rather say it up front: - It is not a prompt-engineering role, and it is not an ML/LLM research role. - It is not a role where green tests are sufficient evidence. On security and performance, "the spec is met and the tests pass" is not a weak signal — it is a null one. - It is not a ticket queue. The profile that shrinks in an AI-native team is the one whose value was implementing assigned tickets between two boundaries. --- ## Our Tech Stack - **Backend:** Node.js / TypeScript - **Frontend:** Vue.js 3 - **Database:** PostgreSQL, MariaDB - **DevOps:** Docker, Kubernetes, Terraform - **Cloud:** GCP **Engineering apparatus you will use and help build:** coding agents orchestrated deterministically in CI, aspect-scoped verification agents (authorization, performance, spec conformance, dependencies), policy-as-code, property-based and contract testing, volumetric test datasets, load and endurance gates on critical paths, feature flags, progressive delivery and end-to-end tracing. --- ## What we offer - Join a fast-growing company in a friendly, international environment — engineering primarily in Paris, with further engineering presence in Berlin, Montreal and Wilmington (DE), and offices across France, Italy, Spain, Germany, Canada, the USA, Mexico and Dubai; - Our "Remote Policy" guarantees that you can find the right balance between "Onsite" and "Remote"; - Last but not least, all the day-to-day benefits of the CSE, luncheon vouchers, profit sharing bonuses, etc... --- ## Recruitment process - Interview with a TA team member (30/45 mins) - Interview with the Engineering Manager (1h) - Technical interview (1h30) — two parts: turning an ambiguous requirement into a specification with executable acceptance criteria, then an adversarial review of an agent-generated diff against that specification - Interview with the CTO (45 mins) ```json {"@context":"https://schema.org","@graph":[{"@id":"https://vuejobs.com/#website","@type":"WebSite","name":"Vue.js Jobs","url":"https://vuejobs.com/","publisher":{"@id":"https://vuejobs.com/#identity"}},{"@id":"https://vuejobs.com/jobs/dilitrust-senior-product-engineer-ai-native#webpage","@type":"WebPage","name":"Senior Product Engineer - AI Native at DiliTrust","url":"https://vuejobs.com/jobs/dilitrust-senior-product-engineer-ai-native","isPartOf":{"@id":"https://vuejobs.com/#website"},"potentialAction":[{"@type":"ReadAction","target":["https://vuejobs.com/jobs/dilitrust-senior-product-engineer-ai-native"]}],"primaryImageOfPage":{"@id":"https://vuejobs.com/#logo"}},{"@id":"https://vuejobs.com/#identity","@type":"Organization","name":"VueJobs","url":"https://vuejobs.com","logo":{"@id":"https://vuejobs.com/#logo"},"sameAs":["https://x.com/vuejsjob","https://www.linkedin.com/showcase/vuejobs/","https://github.com/vuejobs"]},{"@id":"https://vuejobs.com/jobs/dilitrust-senior-product-engineer-ai-native#job-posting","@type":"JobPosting","datePosted":"2026-09-18T13:17:41.000000Z","description":"\u003Ch3>Ready to be part of the Legal Tech revolution?\u003C/h3>\n\u003Cp>\u003Cstrong>Vision:\u003C/strong>\u003C/p>\n\u003Cp>As a leading software-as-a-service (SaaS) provider, DiliTrust is a global company dedicated to offering an integrated suite of legal and governance products. Our vision is to digitize legal departments worldwide. With an annual growth rate of over 40% since 2020, our ambition is to become the world's leading Legal Tech company, aiming for a valuation exceeding $1 billion by 2026.\u003C/p>\n\u003Cp>\u003Cstrong>Our Impact:\u003C/strong>\u003C/p>\n\u003Cp>From generating General Meeting reports to leveraging AI-assisted contract lifecycle management, our teams in our 8 offices across France, the US, Mexico, MEA, Germany, Spain, Italy, and Canada are the driving force behind our global success. We proudly support 2,400 customers in 64 countries, with 80% of our clientele comprising listed companies in major markets such as Europe, North America, and the Middle East.\u003C/p>\n\u003Cp>\u003Cstrong>Our Recognition:\u003C/strong>\u003C/p>\n\u003Cp>DiliTrust has been at the forefront of Legal Tech innovation, being the first Legal Tech with AI features since 2022. The company is renowned for providing a positive and entrepreneurial work environment. We are honored to have received the "Happy at Work" and "Tech at Work" labels every year since 2019.\u003C/p>\n\u003Ch3>The Role:\u003C/h3>\n\u003Cp>Lini is DiliTrust's proprietary AI engine, powering Ask Lini, Risk Detector, Document Summarization, Minute Generation, and every AI capability across the suite.\u003C/p>\n\u003Cp>We are building a dedicated squad around it and are looking for a strong Software / Product Engineer, with a focus our platform architecture, to help us bring it to the next level.\u003C/p>\n\u003Cp>As a Software Engineer work at the intersection of AI, product, and engineering. You will contribute to building, improving, and scaling the features that make Lini a reliable and powerful AI layer across the entire DiliTrust suite.\u003C/p>\n\u003Cp>We are looking for an engineer who writes clean, production-ready code and is comfortable taking ownership of features end-to-end, from technical design to deployment. We also care about how you think about AI: whether you bring genuine curiosity to the product, and whether you can translate a model capability into a great user experience.\u003C/p>\n\u003Chr />\n\u003Ch2>Missions\u003C/h2>\n\u003Cul>\n\u003Cli>\u003Cstrong>Write specifications as the durable asset of the project.\u003C/strong> Executable acceptance criteria, and — crucially — the non-functional requirements that specs almost never carry: data classification, endpoint × role authorization matrix, volumetry assumptions, latency and throughput budgets. These are the requirements whose later correction is superlinear, so they get decided before generation, not after.\u003C/li>\n\u003Cli>\u003Cstrong>Freeze the contracts before any fan-out.\u003C/strong> API schemas, types, module boundaries, invariants. Agents do not negotiate an interface in the hallway: each will make a plausible and incompatible assumption, discovered at integration.\u003C/li>\n\u003Cli>\u003Cstrong>Pilot coding agents with a tight brief and a bounded context\u003C/strong> — narrow tasks, defined input and output artifacts, explicit stop conditions and budgets, full traceability of what produced each change.\u003C/li>\n\u003Cli>\u003Cstrong>Keep producer and verifier separate.\u003C/strong> You do not sign off alone on generation you piloted, and you act as independent verifier on your peers' slices — with an adversarial brief ("find what breaks against this spec"), never "confirm this looks fine".\u003C/li>\n\u003Cli>\u003Cstrong>Build the asymmetric gates that make the slice safe at volume\u003C/strong> — expensive to satisfy, cheap to check: property tests, contract tests, query-count and allocation budgets, execution-plan checks, policy-as-code, backward-compatibility proofs. Written \u003Cem>before\u003C/em> the implementation exists, so the agent closes the feedback loop itself without consuming human attention.\u003C/li>\n\u003Cli>\u003Cstrong>Use code reading as a calibration instrument, not as a gate.\u003C/strong> Sample deliberately, by risk zone, to measure the real defect rate of the generator-plus-gates pair and to keep the team's mental model of its own system alive.\u003C/li>\n\u003Cli>\u003Cstrong>Keep work-in-progress low.\u003C/strong> Capped PR size, thin vertical slices, trunk-based with very short branches, feature flags over long-lived branches, CI as the agent's first task rather than its last. More features in flight does not mean faster delivery when the bottleneck is verification.\u003C/li>\n\u003Cli>\u003Cstrong>Design for blast radius.\u003C/strong> Reversibility, progressive delivery, structured logs, traces, metrics and instrumentation generated as a matter of course. On many paths, detecting in five minutes beats three days of review that prevents nothing.\u003C/li>\n\u003C/ul>\n\u003Chr />\n\u003Ch2>Requirements\u003C/h2>\n\u003Cp>\u003Cstrong>Being based in France with full working rights.\u003C/strong> \u003Cstrong>Fluent in French and English.\u003C/strong>\u003C/p>\n\u003Cp>\u003Cstrong>Experience & Seniority:\u003C/strong>\u003C/p>\n\u003Cul>\n\u003Cli>8+ years of professional software engineering experience, with a significant portion spent building and operating B2B SaaS platforms in production\u003C/li>\n\u003Cli>Proven ownership of features across their full lifecycle — design, delivery, iteration, maintenance — on long-lived, multi-year products\u003C/li>\n\u003Cli>Strong background in complex, scalable web architectures, including real modularity: you have seen where coupling stops parallel work dead\u003C/li>\n\u003C/ul>\n\u003Cp>\u003Cstrong>AI-Native Practice:\u003C/strong>\u003C/p>\n\u003Cul>\n\u003Cli>Demonstrated, sustained use of coding agents in production work — not autocomplete, but delegated implementation with review and accountability\u003C/li>\n\u003Cli>A concrete, articulated view of where generated code fails: correlated defects rather than idiosyncratic ones, uniform surface quality that destroys the usual "look here" review signals, plausibility with no author to interrogate\u003C/li>\n\u003Cli>Comfort being accountable for code you did not author, and the discipline to refuse a change you cannot explain\u003C/li>\n\u003C/ul>\n\u003Cp>\u003Cstrong>Verification & Quality:\u003C/strong>\u003C/p>\n\u003Cul>\n\u003Cli>Real fluency in property-based testing, contract testing, and deriving tests from the specification rather than from the code\u003C/li>\n\u003Cli>Test-data strategy, including maintaining a volumetrically representative dataset as part of the verification apparatus — not a nice-to-have\u003C/li>\n\u003Cli>Instinct for the difference between a rigorous check and a \u003Cem>scalable\u003C/em> one: does the cost of checking grow with the volume produced?\u003C/li>\n\u003C/ul>\n\u003Cp>\u003Cstrong>Security & Performance (non-negotiable on this role):\u003C/strong>\u003C/p>\n\u003Cul>\n\u003Cli>Authorization modelling in multi-tenant systems, and why declarative, centrally enforced authorization beats reviewing each endpoint. Generated code reliably checks \u003Cem>who\u003C/em> you are and regularly forgets \u003Cem>whether you are allowed\u003C/em>\u003C/li>\n\u003Cli>Awareness of the attack surface specific to an agent-assisted pipeline: prompt injection through ticket descriptions, code comments and dependency READMEs; supply-chain risk on hallucinated package names; least privilege for non-human identities; and the most frequent risk of all — production data or proprietary code leaking into the development loop\u003C/li>\n\u003Cli>Performance as a measured number rather than a code-reading opinion: query budgets per HTTP request, N+1, unbounded result sets, missing indexes on new query paths, network calls in loops, execution-plan review. These are invisible at test-data scale and expensive in production\u003C/li>\n\u003C/ul>\n\u003Cp>\u003Cstrong>Product & Team Collaboration:\u003C/strong>\u003C/p>\n\u003Cul>\n\u003Cli>Excellent written communication — specification writing is now a core engineering skill on this role, not documentation overhead\u003C/li>\n\u003Cli>Extensive experience working directly with product managers, designers and stakeholders in a product-oriented setup\u003C/li>\n\u003Cli>Strong sense of ownership and sound judgment on risk: what to build, what not to build, what residual risk is acceptable and why\u003C/li>\n\u003C/ul>\n\u003Cp>\u003Cstrong>Education:\u003C/strong>\u003C/p>\n\u003Cul>\n\u003Cli>Master's degree in Engineering or equivalent practical experience in senior SaaS environments\u003C/li>\n\u003C/ul>\n\u003Chr />\n\u003Ch2>What this role is not\u003C/h2>\n\u003Cp>We would rather say it up front:\u003C/p>\n\u003Cul>\n\u003Cli>It is not a prompt-engineering role, and it is not an ML/LLM research role.\u003C/li>\n\u003Cli>It is not a role where green tests are sufficient evidence. On security and performance, "the spec is met and the tests pass" is not a weak signal — it is a null one.\u003C/li>\n\u003Cli>It is not a ticket queue. The profile that shrinks in an AI-native team is the one whose value was implementing assigned tickets between two boundaries.\u003C/li>\n\u003C/ul>\n\u003Chr />\n\u003Ch2>Our Tech Stack\u003C/h2>\n\u003Cul>\n\u003Cli>\u003Cstrong>Backend:\u003C/strong> Node.js / TypeScript\u003C/li>\n\u003Cli>\u003Cstrong>Frontend:\u003C/strong> Vue.js 3\u003C/li>\n\u003Cli>\u003Cstrong>Database:\u003C/strong> PostgreSQL, MariaDB\u003C/li>\n\u003Cli>\u003Cstrong>DevOps:\u003C/strong> Docker, Kubernetes, Terraform\u003C/li>\n\u003Cli>\u003Cstrong>Cloud:\u003C/strong> GCP\u003C/li>\n\u003C/ul>\n\u003Cp>\u003Cstrong>Engineering apparatus you will use and help build:\u003C/strong> coding agents orchestrated deterministically in CI, aspect-scoped verification agents (authorization, performance, spec conformance, dependencies), policy-as-code, property-based and contract testing, volumetric test datasets, load and endurance gates on critical paths, feature flags, progressive delivery and end-to-end tracing.\u003C/p>\n\u003Chr />\n\u003Ch2>What we offer\u003C/h2>\n\u003Cul>\n\u003Cli>Join a fast-growing company in a friendly, international environment — engineering primarily in Paris, with further engineering presence in Berlin, Montreal and Wilmington (DE), and offices across France, Italy, Spain, Germany, Canada, the USA, Mexico and Dubai;\u003C/li>\n\u003Cli>Our "Remote Policy" guarantees that you can find the right balance between "Onsite" and "Remote";\u003C/li>\n\u003Cli>Last but not least, all the day-to-day benefits of the CSE, luncheon vouchers, profit sharing bonuses, etc...\u003C/li>\n\u003C/ul>\n\u003Chr />\n\u003Ch2>Recruitment process\u003C/h2>\n\u003Cul>\n\u003Cli>Interview with a TA team member (30/45 mins)\u003C/li>\n\u003Cli>Interview with the Engineering Manager (1h)\u003C/li>\n\u003Cli>Technical interview (1h30) — two parts: turning an ambiguous requirement into a specification with executable acceptance criteria, then an adversarial review of an agent-generated diff against that specification\u003C/li>\n\u003Cli>Interview with the CTO (45 mins)\u003C/li>\n\u003C/ul>","employmentType":"FULL_TIME","title":"Senior Product Engineer - AI Native","validThrough":"2026-11-30T13:53:09.496Z","applicantLocationRequirements":{"@type":"Country","name":"FR"},"hiringOrganization":{"@type":"Organization","name":"DiliTrust","logo":"https://assets.jobbb.io/logos/01ke0h2twd697n29zj0jgfwb8c_1767396962.png","url":"https://vuejobs.com/"},"identifier":{"@type":"PropertyValue","name":"DiliTrust","value":"01m2ttd9dyk23bva3s5gp2j1p0"},"jobLocation":{"@type":"Place","address":{"@type":"PostalAddress","addressLocality":"Paris","addressCountry":"FR"}},"mainEntityOfPage":{"@id":"https://vuejobs.com/jobs/dilitrust-senior-product-engineer-ai-native#webpage"}},{"@id":"https://vuejobs.com/#logo","@type":"ImageObject","caption":"VueJobs","contentUrl":"https://vuejobs.com/images/logos/vuejobs-logo.png","inLanguage":"en","url":"https://vuejobs.com/images/logos/vuejobs-logo.png"}]} ``` ## Sitemap See the full [sitemap](https://vuejobs.com/sitemap.md) for all pages.