Member of Technical Staff - Post Training - Mai Superintelligence Team

Microsoft Microsoft · Big Tech · Mountain View, CA +4 · Software Engineering

This role focuses on the post-training of large language models (LLMs) to improve their capabilities in areas like reasoning, instruction following, math, code, and tool use. The responsibilities include data collection, building evaluations, and applying advanced reward modeling and RL techniques. The goal is to advance the state-of-the-art in LLM performance and contribute to the development of superintelligent AI systems.

What you'd actually do

  1. Develop data collection, evaluation, and post-training methods for models.
  2. Design hypotheses and experiment plans for rapidly iterating on model performance.

Skills

Required

  • Bachelor's Degree in Computer Science, Machine Learning, Mathematics, or related technical discipline AND 4+ years technical engineering experience with coding in languages including, but not limited to, C, C++, C#, Java, JavaScript, or Python
  • experience with reward modeling, RL, or other post-training techniques

Nice to have

  • Master's Degree in Computer Science or related technical field AND 4+ years technical engineering experience
  • Demonstrated experience in large-scale AI.
  • Passion for conversational AI and its deployment.
  • Demonstrated written and verbal communication skills with the ability to work closely with cross-functional teams, including product managers, designers, and other engineers.
  • Passion for learning new technologies and staying up to date with industry trends, best practices, and emerging technologies in AI.
  • Proven ability to collaborate and contribute to a positive, inclusive work environment, fostering knowledge sharing and growth within the team.

What the JD emphasized

  • post-training
  • reward modeling
  • RL techniques
  • evaluations
  • data collection

Other signals

  • post-training large language models (LLMs)
  • advance the state-of-the-art
  • reward modeling and RL techniques