San Francisco startup building systems for open-ended task generation

Member of Technical Staff - Mechanistic Interpretability

San FranciscoOn-site$300K - $500K5 - 12 years
You'll spend mornings tracing circuits through transformer attention heads, afternoons probing how latent representations steer task-solving behavior, and evenings debating whether a particular neuron is doing arithmetic or syntax. This is research engineering at the boundary of interpretability and capabilities: building tools that let us actually see what models learn when we train them to generate open-ended tasks. Your work directly shapes how we understand and steer systems that few people have built before.

What they're looking for

  • 5+ years of deep technical work in machine learning, with strong intuition for transformer internals and why they do what they do
  • Published research or substantial open-source contributions in mechanistic interpretability, adversarial robustness, or model internals analysis
  • Expert-level PyTorch and the ability to quickly build and iterate on experimental infrastructure
  • Track record of translating fuzzy research questions into concrete, disprovable hypotheses
  • PhD or equivalent depth of self-directed research experience in a relevant technical field

Tech stack

PythonPyTorch

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.