ellamind

You'll build **evaluation-first AI infrastructure** at ellamind, developing **scalable APIs** and **intuitive interfaces** that make LLM testing rigorous and repeatable. Your work will help teams ship reliable AI with confidence.

You'll build and ship **production AI agents** for regulated industries, working across the stack from frontend to infrastructure. Your core impact is using **agentic coding tools** to improve the agents themselves, feeding learnings back into faster tooling. This role combines **end-to-end ownership** with deep technical work on systems that make real, audited decisions.

You'll embed with customers in regulated industries like health insurers and banks, identifying operational bottlenecks and building **production AI agents** that actually run. You'll scope use cases, prototype rapidly using agentic coding tools, and deploy agents with full audit trails. This role offers a rare chance to shape **agent deployment in high-stakes environments** and influence product direction.

You'll build **evaluation-first AI infrastructure** at ellamind, designing systems that automatically assess LLM outputs for quality and safety. Your work will enable teams to **test, measure, and improve LLM applications** with rigorous, repeatable engineering. You'll collaborate across a Python-based platform with engineers, product teams, and customers to solve real-world AI evaluation challenges.

You'll build **evaluation-first AI infrastructure** for teams testing LLM applications. You'll develop **scalable APIs and intuitive interfaces** to turn ad-hoc experiments into rigorous engineering. This role offers **end-to-end ownership** and collaboration with AI researchers.