Building infrastructure that lets autonomous agents learn continuously, with every decision auditable and verified

AI Research Engineer

Washington DCRemote$130K - $180K1+ years
We're tackling a deceptively hard problem: how do you let an AI agent keep learning in production without ever losing track of why it made a particular choice six months ago? The team is designing systems that marry continual learning with cryptographic verifiability, so agent behavior stays inspectable across millions of interactions. You'll prototype new training pipelines, run rigorous experiments, and shape the core libraries that turn research artifacts into something engineers can actually ship. This is a research engineering role grounded in real constraints—latency, determinism, and correctness all matter.

What we're looking for

  • 1+ years of professional or research experience writing production-quality Python, with comfort in scientific computing stacks (NumPy, PyTorch, JAX, or similar)
  • Familiarity with continual learning, online learning, or reinforcement learning paradigms, and a clear-eyed view of where current methods break down
  • Instinct for rigorous experimentation: you think about baselines, ablations, and statistical significance before you trust a result
  • Comfortable reading recent ML papers and translating ideas into clean, maintainable code without over-engineering
  • Clear written communication—you can document decisions, explain tradeoffs, and collaborate asynchronously across time zones
  • Must be based in the United States.

Tech stack

Python

Apply for this role

This role is one we're recruiting for on behalf of a client company; the client's identity is kept confidential at this stage. A Fluency recruiter will follow up with details.