Senior Machine Learning Engineer, Model Training and Reinforcement Learning
$195k - $262k • Remote • Palo Alto, California, United States
Posted 5d ago
Job Location
Palo Alto, California, United States
Tech Stack
Remote Work Policy
Fully remote
Categories
Machine Learning Engineer
About the job
Nebius is building a full-stack AI cloud platform to support developers and enterprises in AI/ML infrastructure, from data and model training to production deployment. This role focuses on the infrastructure for large-scale AI training and model post-training capabilities, specifically for frontier model improvement. The work involves distributed systems, GPU performance, model training frameworks, RL pipelines, and production engineering. The Senior Machine Learning Engineer will own ML work end-to-end, translating ambiguous goals into concrete experiments, implementing and debugging training and RL recipes, building supporting systems, and delivering measurable improvements in model quality, throughput, and reliability. This is a hands-on role requiring independent debugging of both model behavior and distributed training failures.
Responsibilities
- Design and execute model-training and post-training experiments, including SFT, continued pretraining, preference optimization (DPO/IPO/KTO), and RL methods (RLHF/RLAIF, PPO, 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 implement targeted data, reward, or algorithm improvements.
- Build and maintain distributed training and RL infrastructure using frameworks like Megatron-LM, DeepSpeed, PyTorch FSDP/DTensor, Ray, verl, slime, AReaL, or OpenRLHF.
- Implement and debug parallelism strategies (tensor, pipeline, sequence/context, expert, data parallelism) and develop reliable rollout, reward-serving, checkpointing, and experiment-orchestration components.
- Profile and optimize 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 documents, benchmark reports, and runbooks, and collaborate with research and platform teams.
Requirements
- Strong Python and PyTorch engineering skills, enabling rapid transition from idea to experiment to working system.
- Hands-on experience in at least two of the following areas: model training, post-training/RL, applied modeling, data pipelines, or large-scale ML systems.