Member of Technical Staff - Research, Post-Training

THE ROLE:

We’re building a platform that covers the whole life of an LLM: training it, deploying it, and observing it in production. We already run multi-node training, elastic inference, sandboxes, and distributed volumes, and we control the infrastructure underneath. We’re looking for research depth in post-training to sit alongside our systems and product work.

We are looking for research scientists with a strong track record in reinforcement learning, machine learning, and foundation models, including large language and multimodal models, to join our research team.

WHAT YOU’LL WORK ON:

- Improve existing methods and develop new techniques for large-scale model training, optimization, and inference

- Extend models to long-context and long-horizon tasks

- Improve inference-time efficiency, reliability, and robustness in high-stakes real-world deployments

YOU MAY BE A FIT IF:

- You have a PhD in computer science, machine learning, or a related field

- You have a demonstrated record of research accomplishments in reinforcement learning, machine learning, foundation models, or related fields

- You have experience with large-scale training and inference infrastructure, including distributed systems and multi-node GPU clusters

- You’ve developed, trained, optimized, or deployed state-of-the-art large-scale models

- You have first-author publications at leading venues such as NeurIPS, ICML, ICLR, CoRL, CVPR, UAI, JMLR, or TMLR

- You have a mission-driven mindset and a strong desire to translate research advances into meaningful product impact

- You have a collaborative spirit and can work effectively across research and engineering teams

Candidates with a master’s degree and significant research or industry experience will also be considered.