Member of Technical Staff - Research Engineering

What you'll do

• Design and run post-training experiments, including supervised fine-tuning, reinforcement learning, and distillation.
• Build synthetic data pipelines, agent environments, reward models, verifiers, and benchmarks for training and evaluation.
• Improve experiment and inference efficiency, deploy promising approaches in customer applications, and communicate findings through writing, publications, or open source.

What they ask for

• Practical understanding of modern post-training methods, including RLVR, GRPO, and OPSD, with depth in at least one relevant area.
• Familiarity with PyTorch or JAX training execution and ability to inspect research code and diagnose training problems.
• Experience investigating model training, evaluations, agent environments, or related ML research.
• Strong experimental judgment and ability to plan research, navigate unfamiliar systems, and explain technical decisions.

Nice to have

• Experience with agentic RL, reward modeling, synthetic data, distillation, or efficient inference.
• Research papers, open-source contributions, or independently built systems.

Tools

PyTorch, JAX, RLVR, GRPO, OPSD

AI focus

Post-training specialized language models and agents; researching synthetic data, reinforcement learning, distillation, agent environments, reward models, verifiers, and evaluations.