Software Engineer, Applied AI

Build and improve the core systems behind our agents across retrieval, tool use, document understanding, memory, and orchestration

Design evals and experiments that help us understand agent quality in production

Turn traces, failures, and user behavior into concrete product and architecture decisions

Work closely with operations, GTM, and deployed teams to understand real workflows and where agents break down

Evaluate models, prompts, and system designs across real enterprise tasks

Own the loop from idea -> implementation -> measurement -> iteration

Strong engineering fundamentals and the ability to ship production systems

Fluency in Python

Experience building or working on LLM-powered products, agent systems, or adjacent applied AI systems

An empirical mindset — you reach for logs, traces, experiments, and real usage before guessing

Strong systems taste — you understand that retrieval, prompting, memory, tools, and UX interact

High ownership and comfort working in ambiguity

Strong opinions about what makes agent systems actually work

Experience with retrieval, search, or ranking systems

Experience designing evals, benchmarks, or feedback loops for LLM systems

Experience building internal tools, workflow products, or operator-facing systems

Experience in startups or other high-ownership environments

This is a new field. We care much more about what you have built than whether your background fits a standard template.

Projects that would make us excited include:

Designing and shipping an agent harness that materially improved performance on a real task

Building an eval or benchmark that changed what your team decided to build next

Designing tool interfaces, memory systems, or retrieval systems for an LLM-powered product

Building a production workflow around language models that users actually depended on

Running a careful experiment on prompting, model routing, or orchestration and using it to drive a product decision

If you apply, we would love to see one thing you built with LLMs or agents. It does not need to be perfect or flashy. We mostly want to understand how you think, what you owned, what you learned, and what tradeoffs you made.