Machine Learning Engineer — Reinforcement Learning

Lever, Inc.; Sunnyvale (CA); On-site; USD 150,000 - 450,000; Full time

Benefits offered by this job

Medical benefits

Dental benefits

Vision benefits

Bonus

401K plan

Paid time off

Parental leave

Employee assistance

Life insurance

Disability insurance

Job summary

Institute of Foundation Models is seeking an RL infrastructure engineer to scale end-to-end RL training systems and extend distributed training frameworks across multi-node, multi-GPU clusters.

You will work alongside researchers and engineers to integrate rollout generation, reward computation, and policy updates, while improving reliability, maintainability, and performance of the training stack.

Qualifications

• 5+ years of experience in ML systems, infra, or distributed training.
• Experience modifying distributed ML frameworks (e.g., DeepSpeed, FSDP, FairScale, Horovod).
• Strong software engineering fundamentals (Python, systems design, testing).
• Proven multi-node experience (Slurm, Kubernetes, Ray) and debugging skills (NCCL/GLOO).
• Ability to implement algorithms across GPUs/nodes based on mathematical specs.
• Experience with ML platform/infrastructure or distributed inference optimization teams.
• Hands-on experience developing an LLM RL pipeline across rollout/inference and distributed training integration.
• Working knowledge of policy optimization methods such as PPO or GRPO.

Responsibilities

• Extend or modify training frameworks to support new use cases and architectures.
• Connect training workers with rollout generation engines, including trajectory exchange and policy-weight synchronization.
• Create and debug multi-node launch scripts with flexible batch sizes and hardware targets.
• Build systems for experiment tracking, job monitoring, and logging for collaborators and researchers.
• Write production-quality code and tests for ML infra in PyTorch or JAX, ensuring reliability at scale.
• Implement reward/verifier integration and trajectory processing, validating log probabilities and loss inputs.
• Coordinate rollout and training workers, including checkpoint/restart and failure recovery; track policy versions and sample staleness.

Skills

ML systems

Distributed training

Python

Systems design

Testing

Multi-node experience

NCCL/GLOO debugging

Policy optimization

Tools

DeepSpeed

FSDP

FairScale

Horovod

Slurm

Kubernetes

Ray

Job description

About the Institute of Foundation Models

We are a dedicated research lab for building, understanding, using, and risk-managing foundation models. Our mandate is to advance research, nurture the next generation of AI builders, and drive transformative contributions to a knowledge-driven economy.

As part of our team, you’ll have the opportunity to work on the core of cutting-edge foundation model training, alongside world-class researchers, data scientists, and engineers, tackling the most fundamental and impactful challenges in AI development. You will participate in the development of groundbreaking AI solutions that have the potential to reshape entire industries.Strategic and innovative problem-solving skills will be instrumental in establishing MBZUAI as a global hub forhigh-performance computing in deep learning, driving impactful discoveries that inspire the next generation of AIpioneers.

The Role

We’re looking for an RL infrastructure engineer to help extend and scale our end-to-end RL training systems. You’ll work side-by-side with world-class researchers and engineers to:

• Extend distributed training frameworks (e.g., DeepSpeed, FSDP, FairScale, Horovod)
• Integrate rollout generation, reward computation, trajectory processing, policy updates, and weight synchronization
• Build robust config + launch systems across multi-node, multi-GPU clusters
• Own experiment tracking, metrics logging, and job monitoring for external visibility
• Improve training system reliability, maintainability, and performance

Hands-on experience developing end-to-end RL infrastructure is required. Strong infrastructure and systems experience is what we value most.

Key Responsibilities

• Distributed Framework Ownership – Extend or modify training frameworks (e.g., DeepSpeed, FSDP) to support new use cases and architectures.
• Training & Inference Integration – Connect training workers with rollout generation engines (e.g., vLLM, SGLang), including trajectory exchange and policy-weight synchronization.
• Launch Config & Debugging – Create and debug multi-node launch scripts with flexible batch sizes, parallelism strategies, and hardware targets.
• Metrics & Monitoring – Build systems for experiment tracking, job monitoring, and logging usable by collaborators and researchers.
• Infra Engineering – Write production-quality code and tests for ML infra in PyTorch or JAX; ensure reliability and maintainability at scale.
• RL Pipeline Development – Implement reward/verifier integration and trajectory processing, and validate log probabilities, token masks, and loss inputs with researchers.
• RL Execution & Recovery – Coordinate rollout and training workers, including checkpoint/restart and failure recovery; track policy versions and sample staleness when using asynchronous execution.

Qualifications

Must-Haves:

• 5+ years of experience in ML systems, infra, or distributed training
• Experience modifying distributed ML frameworks (e.g., DeepSpeed, FSDP, FairScale, Horovod)
• Strong software engineering fundamentals (Python, systems design, testing)
• Proven multi-node experience (e.g., Slurm, Kubernetes, Ray) and debugging skills (e.g., NCCL/GLOO)
• Ability to implement algorithms across GPUs/nodes based on mathematical specs
• Experience working on an ML platform/ infrastructure, and/or distributed inference optimization team
• Experience with large-scale machine learning workloads (strong ML fundamentals)
• Hands-on experience developing an LLM RL pipeline, with ownership across rollout/inference and distributed training integration.
• Working knowledge of policy optimization methods such as PPO or GRPO, sufficient to implement and debug sampling, log probabilities, and policy updates.

Nice-to-Haves:

• Exposure to mixed-precision training (e.g., bf16, fp8) with accuracy validation
• Familiarity with performance profiling, kernel fusion, or memory optimization
• Open-source contributions or published research (MLSys, ICML, NeurIPS)
• CUDA or Triton kernel experience
• Experience with large-scale pre-training
• Experience building custom training pipelines at scale and modifying them for custom needs
• Deep familiarity with training infrastructure and performance tuning
• Experience with asynchronous RL, multi-turn or tool-using rollout environments, or custom reward/verifier systems.

$150,000 - $450,000 a year

Salary Range

The posted salary range represents the company’s good faith estimate of the compensation for this position upon hire. The actual compensation offered may vary within this range depending on individual qualifications, including but not limited to relevant skills, experience, education, certifications, geographic location, and specific business needs.

The posted salary range represents the company’s good faith estimate of the compensation for this position upon hire. The actual compensation offered may vary within this range depending on individual qualifications, including but not limited to relevant skills, experience, education, certifications, geographic location, and specific business needs.

Benefits Include

*Comprehensive medical, dental, and vision benefits

*Bonus

*401K Plan

*Generous paid time off, sick leave and holidays

*Paid Parental Leave

*Employee Assistance Program

*Life insurance and disability