Context & agent engineer
Lucis
Paris, France
Posted on Mar 16, 2026
Context & agent engineer
Paris
Engineering
17 hours ago
Hybrid
Full-time
The role
Over the last year, AI went from “helpful tool” to something closer to a new kind of teammate: capable of drafting, coding, analyzing, and operating across many steps when given the right context and guardrails.
We think the next step-function in startup speed will come from teams that operationalize AI well:
- Not one-off prompts.
- Not a few power users.
- But repeatable workflows that the whole company trusts and actually adopts.
This role exists to make that real at Lucis.
We are hiring a Context Engineer / Applied AI lead to make Lucis meaningfully faster and higher quality by embedding AI into how we work.
This is not a pure research role. It is an enablement + systems role:
- You will find high-leverage workflows across teams.
- Turn them into repeatable playbooks and lightweight internal products.
- Put measurement in place.
- Build guardrails so the outputs are reliable, safe, and trustworthy.
You will partner closely with Product, Engineering, Operations, Growth, and Clinical, and report to the CTO.
What you’ll do
- Audit how Lucis uses AI today: What works, what breaks, where it is risky, and where it can be 10x better.
- Ship a Lucis AI playbook: Prompt patterns, examples, do’s and don’ts, safety guidance, and “how we know it works.”
- Roll out 5–10 high-leverage workflows: Across engineering, product spec, support ops, growth, and clinical content.
- Build lightweight internal tools: Automations, scripts, small apps, or integrations that remove repetitive work.
- Measure impact: Adoption, time saved, and quality improvements. You care about “before/after,” not vibes.
- Increase reliability and trust: Guardrails, evaluations, and practical safety practices around sensitive data.
About you
You’re passionate about the future of human health and want your work to help people stay healthy for longer. You move quickly from idea to execution, take full ownership of what you build, and work best with talented people who care as much as you do.
You thrive in fast‑moving environments, learn by doing, and value feedback as a way to continuously improve.
You’ll fit in well if
- Have 3–6+ years in product engineering, platform/devex, technical enablement, or applied AI, with clear evidence of shipped outcomes.
- Are a power user of modern AI tools (Claude, ChatGPT, Cursor, Copilot, v0, etc.) and can explain when they fail and what you do about it.
- Can prototype quickly and ship small improvements weekly.
- Have strong enablement instinctsYou can teach, write clearly, and drive adoption with technical and non-technical teammates.
- Are pragmatic and impact-drivenYou optimize for workflows people use and trust, not novelty.
Bonus points if you
- Have built internal tooling that others rely on day-to-day.
- Have experience with LLM patterns (prompting, RAG, tool calling, agents) and evaluation approaches.
- Have worked in environments with real constraints around data handling, security, or compliance.
- Enjoy being the person who turns “fuzzy” into “shippable.”
Why Lucis
- You’ll work on a mission that matters: helping people take control of their health through better information and guidance.
- You’ll have leverage across the whole company: your work changes how everyone ships.
- You’ll help define our AI operating system from early days.
Our current stack
Python repo and TS monorepo (platform) · PostgreSQL + Prisma · AWS (Terraform) · GitHub Actions · Claude Code + Cursor · AI/agent framework: mostly Langchain ecosystem. N8N for automation. Metabase for reporting.
The process
- Intro call (20 min): culture & role fit.
- Technical interview (30 min)
- At-home case study: hands-on project, delivery in 2 days.
- Deep dive (90 min) and team chat (on-site)
- Reference calls
How we work
We work together from our Paris hub. We’re passionate about what we’re building and believe the fastest way to create something exceptional is side by side. We’re open to relocation support for the right individuals, and we welcome missionaries who travel to work with us in Paris on a regular basis.
- Rigor without ego: Audits, science, and code all deserve the same high bar.
- Radical ownership: Feedback loops are short; everyone contributes to building the best version of Lucis.
- Velocity over perfection: We ship daily and prefer a good decision today over a perfect one next week
At Lucis, AI isn't just our product, it's our engine. 100% of our teams are equipped with the best AI agents. You have carte blanche to explore and automate everything that can be, so you can focus exclusively on high-value work.
Req ID: R12