← All roles

Senior Applied Scientist(Agentic RL & LLM Post-Training)

Microsoft· Applied Sciences
Apply on company site
Suzhou, Jiangsu, China, Beijing, Chinafull-timePosted 1mo ago

About the role

Senior Applied Scientist focusing on agentic reinforcement learning and post-training for large language models to enable planning, tool-use, and multi-step task execution in agentic scenarios. Works on RL post-training, large-scale RL infrastructure, data generation, and evaluation.

Responsibilities

  • Design and run RL post-training for LLM agents on long-horizon, multi-turn, tool-using tasks, such as productivity and document workflows, information seeking, and other complex tasks.
  • Build and scale agentic RL environments, including sandboxed tool execution, task simulators, and trajectory collection that closely reflect real agent behavior.
  • Design reward functions, verifiers, and LLM-as-judge methods for outcome and process supervision that are robust to reward hacking and track real task success.
  • Advance RL algorithms for LLMs (e.g., PPO, GRPO, SAO and variants), including credit assignment over multi-turn trajectories, off-policy correction, and training stability at scale.
  • Explore self-improving agents (e.g., RSI), where models help generate the feedback, data, and tasks that improve them.
  • Build and extend distributed RL training systems for large models, including Mixture-of-Experts architectures.
  • Solve challenging systems problems such as coherence between rollout and training, efficient weight synchronization, long-context training, low-precision and quantization-aware training, and multi-node scaling on large GPU clusters.
  • Build high-quality agentic training data through trajectory synthesis, rejection sampling, and gap-driven data curation.
  • Build rigorous evaluation pipelines and fast iteration loops that connect model improvements to user-facing quality.

Qualifications

  • Master's or PhD in Computer Science, Machine Learning, or a related field, plus 4+ years of hands-on experience with large language models or deep learning (or equivalent experience).
  • Hands-on experience with reinforcement learning for LLMs (e.g., RLHF, RLAIF, RL with verifiable rewards) at meaningful scale.
  • Strong engineering skills in Python (PyTorch), and experience with distributed training on multi-node GPU clusters.
  • Solid understanding of the LLM post-training pipeline, from data and SFT through RL, evaluation, and deployment.

Skills

Required:Large language models / deep learningReinforcement learning for LLMs
Last updated Oct 16, 2026. Interested? Apply on the company site.

About Microsoft

Cloud ComputingConsumer ElectronicsSoftwareTechnologyliquid-ai-recruiting-target
Company profileWebsite

More open roles at Microsoft