What You'll Own
Architect and ship agentic product experiences, building products that the world's largest banks will trust with real work.
Drive critical architectural decisions to balance performance, cost efficiency, and long-term maintainability.
Design and own the harnesses behind every agent: evals, guardrails, tool integrations, and the observability, testing, and safeguards to know exactly what an agent did and why.
Implement these systems directly into our backend: build APIs (Python Django/FastAPI), supporting infrastructure (AWS), and work with product engineers to build out the user interface.
Set the groundwork for our AI org — setting up patterns, systems, and processes that will grow with the company as our engineering team grows.
Stay on the bleeding edge of the AI ecosystem, constantly evaluating new tools, models, and techniques for what can be utilized in our product.
What You'll Need
4+ years building production backend software, with 2+ years shipping LLM-powered features.
Depth with frontier models: prompting, tool use, context management, and building the harnesses around them.
Experience making agentic systems production-grade: evals, guardrails, observability, and failure handling.
Autonomous ownership from conception to production. Small team — you take things start to finish.