Senior Research Engineer

🚀 Senior Research Engineer | Interpretability, Alignment & Experimental AI Systems📍 San Francisco (Onsite)💰 Highly Competitive Compensation + EquityI'm partnering with an early-stage AI research lab tackling one of the biggest challenges in AI today: Understanding what is actually happening inside advanced models.This team is focused on interpretability, alignment, reinforcement learning, and representation engineering, building tools that allow researchers to inspect, measure, and steer model behaviour at the activation level.You'll work on:🔹 Mechanistic interpretability and activation analysis🔹 Experimental RL environments and alignment research🔹 Concept detection, probing, and model steering🔹 Formal methods, program analysis, and verification-inspired approaches to AI safety🔹 Greenfield research systems built from scratchWe're looking for exceptional engineers and researchers from backgrounds including:✔️ AI/ML Research✔️ Interpretability & Alignment✔️ Reinforcement Learning✔️ Programming Languages & Compilers✔️ Formal Verification✔️ Systems & Security ResearchMachine Learning & AI Research:Interpretability researchAlignment or AI safety researchReinforcement learningRepresentation learningExperimental ML systemsSystems & Formal Methods:Programming languages researchCompilers and runtime systemsFormal verificationProgram analysisTheorem provingSecurity researchEngineering & Research Infrastructure:Building experimental software systems from scratchResearch engineering in highly ambiguous environmentsDeveloping tools for scientific discovery and experimentationWorking close to model internals and low-level systemsDesired Experience:Strong software engineering fundamentalsExperience building research prototypes rather than production systemsAbility to independently drive complex technical projectsStrong abstraction and systems thinking skillsExperience working in highly exploratory research environmentsPhD preferred but not required.This Role Is Not:Large-scale distributed training engineeringMLOps or production infrastructureData engineering pipelinesTraditional applied machine learningIncremental product optimisationConventional software verification rolesIf you're interested in understanding how models reason, not just improving what they output and want to work on foundational AI research alongside a highly technical team, I'd love to speak with you.