Staff Researcher - Post-Training LLMs for Production

Mixpeek; San Francisco (CA); On-site; USD 150,000 - 230,000; Full time

Job summary

Modal is building a platform that covers the full life cycle of LLMs—from training to deployment and observability. We already run multi-node training and elastic inference, and we seek a research‑leaning post‑training specialist to join our team in San Francisco or NYC.

You will own hands‑on post‑training research with the research lead, partner with customers and Forward Deployed Engineers, and explore questions like distillation from production traffic, while showing how the platform enables

Qualifications

• A research‑leaning background in post‑training LLMs, with work you can point to.
• Ability to tell which frontier techniques matter to users and which stay academic.
• A track record of shipping research that others can build on.
• The drive to take a research bet from idea to result with minimal hand‑holding.
• Ability to work in person, in our NYC or San Francisco office.

Responsibilities

• Own end-to-end post-training research bets: RL, distillation, long-context models, and routing.
• Collaborate with customers alongside engineers to train models and translate findings into research.
• Expand collaborations with external labs, e.g., ZLab on DFlash.
• Work with engineering to turn research into product capabilities and frameworks.
• Help shape the research agenda to guide Modal's future.

Job description

Modal is building a platform that covers the full life cycle of LLMs—from training to deployment and observability. We already run multi-node training and elastic inference, and we seek a research‑leaning post‑training specialist to join our team in San Francisco or NYC.

You will own hands‑on post‑training research with the research lead, partner with customers and Forward Deployed Engineers, and explore questions like distillation from production traffic, while showing how the platform enables