Senior Machine Learning Engineer, Model Training and Reinforcement Learning

Nebius Token Factory is building an AI training and model post-training capability for frontier model improvement. As a Senior Machine Learning Engineer, you will own substantial ML work end to end, translating ambiguous capability goals into concrete experiments, implementing and debugging training and RL recipes, building supporting data and systems, and delivering measurable improvements in model quality, experiment throughput, and reliability.

Responsibilities:

• Design and run model-training and post-training experiments, including SFT, continued pretraining, preference optimization, and RL methods.
• Build reward functions, judge models, verifiers, task environments, and evaluation sets for reasoning, coding, tool use, and agentic workflows.
• Create synthetic data and data pipelines.
• Analyze model-behavior failures and turn them into targeted data, reward, or algorithm improvements.
• Build and maintain distributed training and RL infrastructure using frameworks such as Megatron-LM, DeepSpeed, PyTorch FSDP/DTensor, Ray, verl, slime, AReaL, or OpenRLHF.
• Implement and debug parallelism strategies and build reliable rollout, reward-serving, checkpointing, and experiment-orchestration components.
• Profile and improve GPU utilization, memory usage, communication efficiency, training throughput, and inference/serving performance.
• Design rigorous evaluations and ablations for capability, instruction following, reasoning, tool use, safety, and regression risk.
• Write clear experiment plans, design docs, benchmark reports, and runbooks, and partner across research and platform teams.

Requirements:

• Strong Python and PyTorch engineering skills.
• Hands-on experience across at least two of: model training, post-training/RL, applied modeling, data pipelines, or large-scale ML systems.
• Ability to design rigorous experiments with baselines, ablations, metrics, and failure analysis.
• Practical understanding of modern LLM behavior, instruction tuning, preference optimization, and evaluation challenges.
• Practical understanding of transformer training bottlenecks, memory pressure, communication overhead, and checkpointing.
• Ability to reason quantitatively about model quality, throughput, utilization, reliability, cost, and research velocity.
• Strong communication skills and ability to collaborate with researchers, engineers, and leadership.

Nice-to-haves:

• Experience with LLM post-training, RL, agents, reward modeling, synthetic data, or model evaluation.
• Experience with RL frameworks or pipelines such as verl, slime, AReaL, OpenRLHF, TRL, or custom PPO/GRPO/RLHF systems.
• Experience with Megatron-LM, DeepSpeed, PyTorch FSDP/DTensor, Ray, Slurm, or Kubernetes on large GPU clusters.
• Familiarity with NCCL, CUDA, Triton, Nsight, InfiniBand/RDMA, and H100/H200/B200 clusters, or with model serving and inference optimization.

Benefits:

• Health insurance: 100% company-paid medical, dental, and vision coverage for employees and families.
• 401(k) plan: Up to 4% company match with immediate vesting.
• Parental leave: 20 weeks paid for primary caregivers, 12 weeks for secondary caregivers.
• Remote work reimbursement: Up to $85/month for mobile and internet.
• Disability & life insurance: Company-paid short-term, long-term and life insurance coverage.