Applied Research - Forward-Deployed RL
Core
Own applied RL programs from ambiguous customer problems through deployed improvement loops, turning workflows into measurable environments and post-training experiments.
Role type
Senior Applied Research Engineer (Reinforcement Learning & Post-Training)
Builds
Post-training experiments, agent systems, evaluation environments, and reusable platform capabilities for frontier AI.
Domain
Frontier AI, Reinforcement Learning, Agent Systems, Post-Training
Deliverable
production ML models
Required skills
Reinforcement Learning, Post-training (SFT/Distillation), Agent Systems, Python, Experimental Design, Model Debugging, Deployment
Preferred skills
Customer-embedded technical work, Technical founding experience, Applied ML consulting, Open-source contributions
Technologies
Python, RL frameworks, Agent frameworks, Evaluation harnesses
Responsibilities
Define research plans and success measures for customer workflows, run post-training experiments against baselines, deploy results and measure impact, convert recurring parts into reusable platform capabilities, debug model vs. task failures.
Seniority
Senior, hands-on IC with external-facing impact
