Looking for an ML Engineer to join my Online RL team for GigaChat.

We are developing post-training for large language models, including various online RL approaches, and are looking for someone who can not only implement ready-made ideas but also independently lead work from hypothesis to measurable model quality improvement.

What you will do:

• Develop and improve online RL methods: RLHF and GRPO family algorithms
• Build a complete training loop: rollouts, reward signals, validators, and model updates
• Design experiments and understand why a result worked or didn't work
• Develop robust and reproducible training infrastructure
• Optimize distributed training, throughput, and GPU utilization

We are looking for a strong engineer with good knowledge of Python and PyTorch, experience in LLM post-training / online RL / RLHF, and the ability to independently conduct ML experiments from hypothesis formulation to conclusions.

Experience with the following will be a plus:

• GRPO and similar policy optimization approaches
• Reward models
• LLM-as-a-judge
• Validators for general-domain tasks
• vLLM, SGLang, verl, Megatron, or TRL.

Why join us:

• Direct impact on GigaChat's quality
• Combination of research and engineering work
• Complex tasks on large models and a scalable infrastructure
• A strong team of engineers and researchers

If you are interested in developing online RL and turning research ideas into working solutions, message me directly.