Member of Technical Staff, Post-Training

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 post-training work on large language models, with a strong focus on reinforcement learning. You will develop and run the training recipes that turn strong base models into reliable, high-performing agents for real-world tasks. You will also drive the research and implementation of building systems to improve and supervise the post-training pipeline itself. You will own model quality end to end, from environments and rewards through to evaluation. Your work will directly shape the agents our customers rely on in production.

Responsibilities

• Design and run RL-based post-training that improves reasoning, tool use, and long-horizon agent performance.
• Develop and refine training recipes, choosing the right methods for each problem rather than defaulting to one approach.
• Design reward signals, graders, and verifiers for customer and domain-specific tasks.
• Drive development of safe automated training pipelines that scale across customers and domain-specific tasks with minimal human intervention.
• Work tightly integrated with synthetic data pipelines, production data, and evaluation.
• Work closely with the RL infrastructure team to scale training runs and improve tooling.
• Support the development of automated pipelines for building training environments and designing reward signals
• Set research and engineering standards and mentor other engineers as the team grows.

Qualifications

• Deep, practical experience applying reinforcement learning to language models shown through shipped models, releases, or publications.
• Strong intuition for loss and reward design, and for how training choices affect model behavior, quality, and reliability.
• Experience training models for reasoning or agentic tasks.
• Strong Python and PyTorch/Jax skills, and experience with distributed training.
• 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

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