About Alan
Alan is building the new standard in prevention insurance, integrating insurance, prevention, and care into a single user experience. Alan partners with 40K+ companies, serves more than 1M+ members, and has reached €800M+ in ARR. The team has 1000+ people, hiring across France, Spain, Belgium, Canada, and beyond.
The Engineering team
In the engineering team, Alaners build the infrastructure, interfaces, and applications to provide first-class service to members, health professionals, and themselves. Engineers work closely with product, move fast with a lot of ownership, and tackle big problems. Those who make product decisions are the same ones who build them.
The stack
Python services on FastAPI, async SQLAlchemy and PydanticAI, Temporal for durable execution, PostgreSQL, MCP, Daytona sandboxes, various LLM model providers, Terraform on AWS, React with Vite. The main backend is a Flask monolith. Alan deploys daily and believes in distributed ownership: you build it, you own it.
The Agentic Platform area
In 2027, Alan expects to run more AI agents than it has employees. Agents already do real work at Alan: they answer members' health questions, resolve support requests, read medical documents, detect fraud, automate operational tasks, and write a large share of the code. Every team building an agent ends up solving the same hard problems: calling models safely with health data, giving agents tools and the right permissions, knowing whether a prompt change made it better or worse, and debugging what it did. This resulted in several agent frameworks and evaluation stacks, each with its own security and compliance story.
The Agentic Platform area was created to fix that. Its mission: make it cheap, fast and safe for every Alaner or crew to build, run and improve agentic products and workflows. The area owns the environment agents run in (infrastructure, runtime, evaluation, observability, skills lifecycle), with security, privacy and compliance by design, and the generalist products on top: Hopper and the Agent Studio. Product teams and all Alaners own their agents, skills, and their outcomes; the Agentic Platform area gives them the paved road.
Two crews, one team:
•Hopper is every Alaner's AI companion. Five months after it started, 80% of Alaners use it, 3k sessions are created each day, and about 30% of pull requests are opened from it.
•AI Product Platform builds the shared blocks every AI product at Alan runs on. For instance, ops teams now build agents autonomously on the Ops AI Platform.
Задачи / Responsibilities
Run agents at scale
•One runtime for every AI product: a shared agent framework, from a single model call to multi-agent workflows with live streaming, and one gateway to every model — routing, failover across providers, quotas and cost per use case built in.
•Agent sessions that last for hours: durable sessions, started from the web, Slack, Linear or GitHub, that survive pod restarts and deploys, and pick up exactly where they left off.
•Sandboxes at scale: an isolated environment for every agent session and every evaluation, on infrastructure compliant with sensitive data, with negligible boot overhead.
Make agents trustworthy and proactive
•One tool gateway to the whole company: an MCP gateway that connects agents to internal tools and data, external services, computer use, managing identity and credentials.
•Agents safely acting on critical data: each agent gets no more than the access it needs; every tool call goes through identity, permissions, confirmations and audit, with no sensitive data leaks.
•Evals you can replay in time: re-run an agent or skill against production as it was at a past point in time, on real data, safely isolated, so anyone can ship knowing their change is an improvement rather than a regression.
•Agents and skills that proactively fix themselves: every run is traced, and every human correction, failed tool call or escalation becomes a prioritized fix that Hopper can apply.
Put agents in everyone's hands
•Skills as a product: a registry where Alaners and teams publish, share and version their skills, so nothing needs to be repeated twice.
•AI that non-engineers can own: Alaners who ship code through Hopper, Operators or Sales who build their own agents or skills in the Studio and operate them from their day-to-day tools.
•Automations and artifacts: agents that run on a schedule or on an event, and build the dashboards and hosted sites that become the go-to places for collaboration.
Is it you we're looking for?
•Own some of the problems above end to end, from design to production, with significant influence on architecture and code quality
•Work closely with the people who use what you build: Alaners, product teams, ops
•Own reliability, cost and security in production
•Mentor engineers, contribute to the product and engineering culture, and help build the team
Требования / Requirements
•3+ years in software engineering, with solid backend fundamentals
•Platform-leaning or product-leaning: both are welcome
•Depth in at least one of: distributed systems and runtimes, evaluation and data quality, security and authorization, product UX
•A good sense of user and developer experience, whatever you build
•You built products, platforms or infrastructure used by other people
•Experience with LLM APIs, agent frameworks, evals or MCP is a strong plus; ML or MLOps experience is a plus
Mindset valued
•You measure success by adoption, not by what is available
•You make concrete tradeoffs between speed, reliability, cost, security and user experience
•You simplify complexity with clear abstractions and maintainable code
•You care about whether people can understand and verify what an AI system did
•You keep up with the latest AI technology and know the open-source AI ecosystem
•Self-directed, pragmatic, humble, collaborative, enthusiastic about learning and teaching
•Excited about AI changing who can build, investigate and automate work
•Above all, high potential and curiosity are valued — everything else is a bonus
•You should be fluent in English (no French required)
Условия / Conditions
•Location: you must be legally eligible to work in France, Belgium, or Spain
•Remote work: remote work flexibility is offered, but in-person collaboration is valued
•Fair rewards: generous equity packages complement the base salary
•Flexible office: office space at HQ, sponsored co-working hubs, or a full-remote experience with home office equipment sponsorship
•Equipment: top of the range equipment — MacBook Pro, keyboard, laptop stand, monitor, and noise-canceling headphones
•Flexible vacation policy and flexible working hours
•Healthcare insurance: comprehensive health insurance, 100% for you and your children, 90-100% for partners depending on country (permanent contracts only)
•Transport: country-specific commuter benefits
•Learning & training: flexible training policy, free books, budget to attend and speak at conferences
•Personal growth through coaching: every Alaner is paired with a dedicated coach from day one
•Parental leave: extended parental leave for all new parents
Note: while applying for a specific area, candidates may join a different engineering team based on where they will have the most impact.
