Member of Technical Staff, Agents & Recursive Self-Improvement (RSI)

About Us

We are a small team of researchers and engineers focused on pushing the frontier of what agents are capable of. We believe the next leap in agent performance will come not from bigger general models, but from specialization and continual learning: agents that get better at their specific job the more they do it. We build the systems that make this possible, turning real-world usage into lasting improvement.

Summary

We are looking for researchers with a strong engineering background to lead agent and self-improvement work on large language models, with a strong focus on systems that get better without human intervention. You will drive the research and implementation of agent pipelines, harnesses, and systems around language models that recursively improve how our agents are built, trained, evaluated, and deployed. You will own the self-improvement loop end to end, from production usage through to the improvements that ship. Your work will directly shape the agents our customers rely on in production.

Responsibilities

• Design and build agent pipelines, harnesses, and systems around large language models for long-horizon, real-world tasks.
• Build agents that automate parts of the ML lifecycle, including data curation, training optimization, debugging, model selection, and experiment execution.
• Develop mechanisms for agents to improve from their own experience, including memory, skill acquisition, and self-generated feedback.
• Identify the highest-leverage improvement opportunities across the stack, from post-training and evaluation to agent harnesses and runtimes, and close the loops between them.
• Work closely with colleagues across post-training, data, and evaluation to turn self-improvement results into shipped improvements.
• Set research and engineering standards and mentor other engineers as the team grows.

Qualifications

• Deep, practical experience building agent pipelines, harnesses, or autonomous systems for language models, shown through shipped products, releases, or publications.
• Strong intuition for how agent design, tools, and feedback loops affect model behavior, quality, and reliability, and how agent design interacts with training and data.
• Experience with ML at both the application and system level, across training, evaluation, and deployment.
• Strong Python skills, and experience with distributed systems and large-scale experiment infrastructure.
• Strong experimental design skills and a disciplined approach to evaluation.
• Able to deeply understand research papers and turn them into working, efficient code.

Nice to Have

• Agent or automation experience at a frontier lab or on widely used open-source agent frameworks.
• Publications at top ML conferences or well-known technical blog posts.
• Experience building agents for long-horizon, multi-step tasks.
• Experience with continual learning or improving models from real-world feedback.