m) -Automated Resolution

Alan

3d•Hybrid

About The Position

Alan is building the new standard in prevention insurance, integrating insurance, prevention, and care into a single user experience. The company is on a journey to build a global leading company with a unique culture. The product team builds AI agents that answer members' questions about their health insurance, with the goal of increasing the quality of answers and the trust members place in them, and making these agents work with other AI agents at Alan. The role involves designing and shipping LLM-powered agents, making agents interoperate with other AI agents, bringing automated resolution to new channels like AI phone support, owning evaluation through datasets and quality monitoring, and measuring/improving resolution rate, answer quality, and member satisfaction. This role offers direct impact on members getting help instantly and drives Alan's scaling, growth, and profitability. It involves applied AI at scale in a regulated, high-stakes domain, tackling frontier problems in production LLM systems, and offers opportunities for ownership and growth.

Requirements

5+ years building scalable software systems
Strong backend experience (Python is a plus)
Hands-on experience building products with LLMs (agents, tool calling, RAG, prompt engineering, evaluation) - ideally shipped to production
An evaluation mindset: you know how to measure whether an AI system is actually good, and how to make it better
You love turning complex problems into elegant solutions
You care about the "why" behind what you build, not just the "how"
You stay on top of a fast-moving AI landscape and are pragmatic about what really works
Humble and still willing to grow (no matter your seniority)
Healthcare technology excites you
You understand that insurance isn't just about money - it's about access to care
High potential and curiosity
Must be legally eligible to work in France, Belgium or Spain.

Responsibilities

Design and ship LLM-powered agents that understand a member's request, reason over their contract, claims and history, and take real actions on their behalf - building the tools, retrieval and context pipelines that give them the right information at the right moment
Make our agents interoperate with other AI agents across Alan, such as Mo: handing off conversations, sharing context and calling each other's capabilities, so members get one seamless experience
Bring automated resolution to new channels, starting with AI phone support: real-time voice conversations with the same quality bar as written ones
Own evaluation: build datasets, automated evals and quality monitoring so we know an agent is right before members see it
Measure and improve resolution rate, answer quality and member satisfaction in production, iterating fast on prompts, models and architecture
Work hand in hand with care experts and product to identify the next topics the AI can fully resolve