The Role
Build and scale end-to-end reinforcement learning infrastructure for foundation models. Responsibilities include extending distributed training frameworks, integrating rollout and inference systems, implementing reward and trajectory processing, configuring multi-node GPU launches, monitoring experiments, optimizing performance, and developing checkpointing and failure-recovery systems. The role requires strong Python and ML systems engineering experience, hands-on LLM RL pipeline ownership, and expertise with distributed training and policy optimization methods.
Summary Generated by Built In
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 for high-performance computing in deep learning, driving impactful discoveries that inspire the next generation of AI pioneers.
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
- 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.
Must-Haves:
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
Skills Required
- 5+ years of experience in ML systems, infrastructure, or distributed training
- Experience modifying distributed ML frameworks such as DeepSpeed, FSDP, FairScale, or Horovod
- Strong software engineering fundamentals, including Python, systems design, and testing
- Proven multi-node experience with Slurm, Kubernetes, or Ray
- Strong debugging skills with NCCL or GLOO
- Ability to implement algorithms across GPUs and nodes from mathematical specifications
- Experience working on an ML platform, ML infrastructure, or distributed inference optimization team
- Experience with large-scale machine learning workloads and strong ML fundamentals
- Hands-on experience developing an LLM reinforcement learning pipeline across rollout, inference, and distributed training integration
- Working knowledge of policy optimization methods such as PPO or GRPO
- Experience with mixed-precision training such as bf16 or fp8 and accuracy validation
- Familiarity with performance profiling, kernel fusion, or memory optimization
- Open-source contributions or published research in venues such as MLSys, ICML, or NeurIPS
- CUDA or Triton kernel experience
- Experience with large-scale pre-training
- Experience building and customizing large-scale training pipelines
- Deep familiarity with training infrastructure and performance tuning
- Experience with asynchronous RL, multi-turn or tool-using rollout environments, or custom reward and verifier systems
Am I A Good Fit?
Get Personalized Job Insights.
Our AI-powered fit analysis compares your resume with a job listing so you know if your skills & experience align.
Success! Refresh the page to see how your skills align with this role.
The Company
What We Do
First a passion, then an idea transformed into success – when it comes to pioneering automation and digitalisation technology, the ifm group is the ideal partner. Since its foundation in 1969, ifm has developed, produced and sold sensors, controllers, software and systems for industrial automation and for SAP-based solutions for supply chain management and shop floor integration worldwide. As one of the pioneers of Industry 4.0, ifm develops and implements consistent solutions to digitalise the entire value chain “from sensor to ERP”. Today, the second-generation family-run ifm group has more than 8,750 employees and is one of the worldwide market leaders. The group combines the internationality and innovative strength of a growing group of companies with the flexibility and close customer contact of a medium-sized company.
