Senior AI Engineer — GenAI & Autonomous Agents

Jus Mundi is building the AI layer for international law and arbitration, turning a vast, multilingual corpus of case law, treaties, and legal analysis into answers practitioners can trust. Founded in 2019 and headquartered in Paris (with offices in New York, London, and Singapore), the company serves 150,000+ users across 90+ countries and recently raised a $22M Series B.

This is a hands-on senior role that owns applied AI systems end to end: search relevance and retrieval, RAG over legal documents, autonomous research agents, and the evaluation harnesses that keep them accurate. You take ambiguous problems ("make our search more relevant", "let users ask a question and get a cited answer") and turn them into concrete technical roadmaps, then ship them to production with measurable impact.

What you'll do:

• Search & Retrieval Relevance: improve retrieval and ranking over a multilingual legal corpus; design and iterate RAG pipelines.
• Agent Orchestration: design agentic systems including orchestration loops, tool calling, memory management, and multi-step reasoning.
• Evaluation & Benchmarking: design rigorous evaluations, understanding metric validity and hallucination prevention.
• Fine-Tuning & Synthetic Data: fine-tune models (LoRA/QLoRA) and generate training data with informed trade-offs.
• Production & LLMOps: deploy features managing latency, cost, and reliability.
• Cross-Squad Leverage: build shared tooling and patterns for other teams.
• Technical Leadership: mentor engineers and contribute to hiring.

What we're looking for:

• Proven track record shipping LLM-powered production features.
• Strong command of vector databases and RAG architecture.
• Deep hands-on expertise with agent orchestration loops, tool calling, memory, and planning: you must be able to point to something you have actually built and shipped.
• Deep understanding of evaluation methodology and benchmark design.
• Demonstrated fine-tuning experience (LoRA/QLoRA) and synthetic data generation.
• Strong Python for AI/backend work, plus full-stack fluency (TypeScript/Node, React).
• Systems thinking for scalability and graceful degradation, plus senior-level behaviors (roadmap development, stakeholder communication, mentoring).

Nice to have: legal-tech or high-stakes domain experience, multilingual NLP/retrieval, model inference optimization (vLLM, TensorRT-LLM), cloud infrastructure (AWS, GCP, Azure) and containerization, open-source AI contributions.

Benefits: 5 weeks annual vacation, 100% private health insurance (employee + children), 60% company-funded meal vouchers, ClassPass co-financing, 8 weeks/year international remote, relocation assistance to France, ongoing training, and company summits.