Karve
Browse all jobs

AI Researcher - Post-Training

Sonar · London

2 months ago

OnsiteFull_timellm post-trainingagentic codingreinforcement learning

Workplace

Onsite

Employment

Full_time

Location

London

Posted

2 months ago

Summary

Senior AI researcher role focused on large language model post-training for enterprise-grade coding agents and models. You will work with Python, policy optimization, verifier-based reinforcement learning, supervised fine-tuning, and static analysis alongside researchers and engineers.

Responsibilities

  • Develop post-training products for coding agents
  • Design hypotheses and run research experiments
  • Iterate proofs of concept into prototypes
  • Convert successful prototypes into products
  • Share research ideas across disciplines
  • Explain technical concepts to varied audiences
pythonrustc#c++javascripttypescriptjavagrpopporlvrsftsynthetic datadata curationpeftpreference alignmentsafety alignmentstatic analysismlops
llm post-trainingagentic codingreinforcement learningsynthetic datastatic analysiscode generation