Senior Machine Learning Engineer, Model Training and Reinforcement Learning

Details

Nebius is building a full-stack AI cloud platform supporting developers and enterprises from data and model training through production deployment. The Token Factory team is building AI training and model post-training capabilities for frontier model improvement.

This role owns the infrastructure that makes large-scale training and reinforcement learning experiments possible, reliable, reproducible, and efficient. The work sits at the intersection of distributed systems, GPU performance, model training frameworks, reinforcement learning pipelines, and production engineering.

A Senior Machine Learning Engineer owns substantial machine learning work end to end, translating ambiguous capability goals into experiments, implementing and debugging training and reinforcement learning 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 supervised fine-tuning (SFT), continued pretraining, preference optimization (DPO, IPO, and KTO), and reinforcement learning methods such as RLHF, RLAIF, PPO, and GRPO.
• 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, including teacher-student generation, self-play, rejection sampling, filtering, and quality scoring.
• Analyze model-behavior failures and turn them into targeted data, reward, or algorithm improvements.
• Build and maintain distributed training and reinforcement learning infrastructure using frameworks such as Megatron-LM, DeepSpeed, PyTorch FSDP/DTensor, Ray, verl, slime, AReaL, or OpenRLHF.
• Implement and debug tensor, pipeline, sequence/context, expert, and data parallelism strategies.
• 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 experiment plans, design documents, benchmark reports, and runbooks, and collaborate with research and platform teams.

Requirements

• Strong Python and PyTorch engineering skills, with the ability to move quickly from an idea to an experiment and working system.
• Hands-on experience in at least two of the following areas: model training, post-training or reinforcement learning, applied modeling, data pipelines, or large-scale machine learning 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, reinforcement learning, agents, reward modeling, synthetic data, or model evaluation.
• Experience with reinforcement learning frameworks or pipelines such as verl, slime, AReaL, OpenRLHF, TRL, or custom PPO, GRPO, or 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, or B200 clusters, or with model serving and inference optimization.
• Publications, open-source contributions, or production impact in LLM post-training, reinforcement learning, reasoning, coding models, synthetic data, distributed training, or evaluation.
• Experience designing agent environments, tool-use tasks, or verifier-based rewards.

Compensation

The base compensation range is $195,200–$262,200 USD. Actual compensation will be determined based on experience, skills, qualifications, hiring level, and geographic location.

Benefits

• 100% company-paid medical, dental, and vision coverage for employees and families.
• 401(k) plan with up to a 4% company match and immediate vesting.
• 20 weeks of paid parental leave for primary caregivers and 12 weeks for secondary caregivers.
• Remote work reimbursement of up to $85 per month for mobile and internet.
• Company-paid short-term disability, long-term disability, and life insurance coverage.
• Career growth and learning opportunities.
• Flexibility and ownership.
• Collaborative and innovative culture.
• Opportunity to work on impactful AI projects.
• International environment and talented teams.

Nebius is an equal opportunity employer committed to fostering an inclusive and diverse workplace. Applicants must be authorized to work in the country in which they apply and must provide proof of employment eligibility as a condition of hire.