Applied RL Training
תיאור המשרה
This is a rare opportunity to work at the intersection of offensive security and AI - and to have your expertise shape a platform used at enterprise scale. Your work will be deployed and used to hack into applications and systems in the real world.ResponsibilitesDesign and implement reinforcement learning workflows to train state-of- the-art LLMs specializing in cybersecurity. Design tasks, datasets, and benchmarks for training and evaluating LLMs and agents.Work on experimentation and evaluation systems - evals are key to everything we do.
In this role, you will build evaluation pipelines, design and build experiments, and construct simulations.Requirements: Strong understanding of modern LLMs, including training, post-training, RL, fine-tuning, and inference, with hands-on experience deploying LLM-based systems in production.Hands-on experience building an agent, including working with complex loops, context engineering, and long-execution tooling.5+ years of hands-on programming experience in Python or other backend languages. Strong fundamentals in system design, performance, and debugging.Experience with data systems and data modeling (databases, pipelines, etc.).Real-world experience running experiments, measuring outcomes, and iterating.This position is open to all candidates.
מתעניינים במשרה הזו?