Senior Machine Learning Researcher

About the role

Toloka is looking for a Senior ML Researcher to own the end‑to‑end fine‑tuning, reinforcement‑learning and evaluation stack that powers our AI‑driven data platform. You will bridge applied research and product engineering, turning complex experiments into scalable platform features.

Key responsibilities

• Design, implement and maintain fine‑tuning pipelines, including data preparation, SFT/LoRA training, model distillation and serving hand‑off.
• Extend the post‑training stack with RL methods (RFT/GRPO), reward modeling and LLM‑judge‑based rewards, and create the user‑facing RL workflow.
• Build and calibrate evaluation harnesses such as LLM‑as‑judge setups, golden datasets and regression evaluations.
• Improve the platform’s guiding agent through prompt and tool design, driven by evaluation feedback.
• Collaborate with clients and internal teams to deliver both self‑serve capabilities and hands‑on solutions.

Required profile

• Proven experience in applied machine‑learning research and product development.
• Track record of delivering greenfield ML projects from research to production.
• Strong analytical mindset with the ability to translate experimental results into platform features.

Required skills

• SFT (Supervised Fine‑Tuning) and LoRA training techniques.
• Model distillation from frontier models to smaller, cost‑effective versions.
• Reinforcement learning methods, including RFT/GRPO‑style approaches.
• Reward modeling and LLM‑as‑judge evaluation frameworks.
• Prompt engineering and tool design for LLM‑driven agents.