D
Staff Product Engineer - AI Native
Contract type
Ongoing
Work mode
Hybrid · Paris - La Défense, France
Experience
Senior · 8+ years
Job description
Software / Product Engineer in a dedicated squad around Lini, DiliTrust's proprietary AI engine, focused on platform architecture and on building, improving and scaling AI features across the suite. The role centres on specification writing, contract design, piloting coding agents and independent verification of generated code.
At a glance
- Employment
- Full-time · Employee (employment agreement)
- Work mode
- Hybrid · Paris - La Défense, France
- Languages
- French – fluent, English – fluent
What you'll do
- Write specifications as the durable asset of the project, including executable acceptance criteria and non-functional requirements: data classification, endpoint × role authorization matrix, volumetry assumptions, latency and throughput budgets
- Freeze the contracts before any fan-out: API schemas, types, module boundaries, invariants
- 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: act as independent verifier on peers' slices with an adversarial brief
- Build asymmetric gates that make the slice safe at volume — property tests, contract tests, query-count and allocation budgets, execution-plan checks, policy-as-code, backward-compatibility proofs — written before the implementation exists
- Use code reading as a calibration instrument, sampling deliberately by risk zone to measure the real defect rate of the generator-plus-gates pair
- Keep work-in-progress low: capped PR size, thin vertical slices, trunk-based with very short branches, feature flags, CI as the agent's first task
- Design for blast radius: reversibility, progressive delivery, structured logs, traces, metrics and instrumentation
- Contribute to building, improving and scaling the features that make Lini a reliable and powerful AI layer across the DiliTrust suite
- Take ownership of features end-to-end, from technical design to deployment
- Work directly with product managers, designers and stakeholders in a product-oriented setup
- Use and help build the engineering apparatus: coding agents orchestrated deterministically in CI, aspect-scoped verification agents, policy-as-code, property-based and contract testing, volumetric test datasets, load and endurance gates, feature flags, progressive delivery and end-to-end tracing
What we're looking for
- Being based in France with full working rights
- Fluent in French and English
- 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
- Demonstrated, sustained use of coding agents in production work — delegated implementation with review and accountability
- A concrete, articulated view of where generated code fails: correlated defects, uniform surface quality, 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
- 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
- Instinct for the difference between a rigorous check and a scalable one
- Authorization modelling in multi-tenant systems, and why declarative, centrally enforced authorization beats reviewing each endpoint
- 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; production data or proprietary code leaking into the development loop
- Performance as a measured number: query budgets per HTTP request, N+1, unbounded result sets, missing indexes on new query paths, network calls in loops, execution-plan review
- Excellent written communication — specification writing is a core engineering skill on this role
- 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
- Master's degree in Engineering or equivalent practical experience in senior SaaS environments
Your team
Lini squad
A dedicated squad built around Lini, DiliTrust's proprietary AI engine powering Ask Lini, Risk Detector, Document Summarization, Minute Generation and every AI capability across the suite.
Benefits
- Remote Policy guaranteeing the right balance between Onsite and Remote
- Day-to-day benefits of the CSE, luncheon vouchers, profit sharing bonuses
How to get hired
- 1Interview with a TA team member (30/45 mins)
- 2Interview with the Engineering Manager (1h)
- 3Technical interview (1h30) — turning an ambiguous requirement into a specification with executable acceptance criteria, then an adversarial review of an agent-generated diff against that specification
- 4Interview with the CTO (45 mins)
Apply
About DiliTrust
Ready to be part of the Legal Tech revolution?
DiliTrust is a global software-as-a-service (SaaS) provider offering an integrated suite of legal and governance products, with an annual growth rate of over 40% since 2020. It was the first Legal Tech with AI features since 2022 and has received the "Happy at Work" and "Tech at Work" labels every year since 2019.
Mission
Digitize legal departments worldwide.
Key facts
- Legal Tech / SaaS
- Annual growth rate of over 40% since 2020
- Ambition to become the world's leading Legal Tech company, aiming for a valuation exceeding $1 billion by 2026
- First Legal Tech with AI features since 2022
- Received the "Happy at Work" and "Tech at Work" labels every year since 2019
- Lini is DiliTrust's proprietary AI engine, powering Ask Lini, Risk Detector, Document Summarization and Minute Generation
What they value
- Positive and entrepreneurial work environment