Research Engineer (Infrastructure RL Systems)

TL;DR

Research Engineer (Infrastructure RL Systems): Design and build scalable, efficient infrastructure for large-scale reinforcement learning training and post-training workloads with an accent on reliability, observability, and orchestration. Focus on optimizing distributed RL training pipelines, collaborating with researchers, and building production-grade systems for stable and fast reinforcement learning.

Location: San Francisco, California, USA

Salary: $350,000 - $475,000 USD per year

Company

hirify.global advances collaborative general intelligence by building scalable AI infrastructure and widely used AI products and open-source projects.

What you will do

• Design, build, and optimize infrastructure for large-scale reinforcement learning and post-training workloads.
• Improve reliability, scalability, and throughput of RL training pipelines and distributed workloads.
• Develop monitoring and observability tools to ensure high uptime and debuggability.
• Collaborate with researchers to translate algorithms into production-grade training pipelines.
• Build evaluation and benchmarking infrastructure for model progress on helpfulness, safety, and factuality.
• Publish learnings through documentation, open-source libraries, or technical reports.

Requirements

• Location: Must be based in San Francisco or able to work onsite.
• Bachelor’s degree or equivalent in computer science, engineering, machine learning, or related fields.
• Strong engineering skills with ability to write performant, maintainable code and debug complex systems.
• Understanding of deep learning frameworks such as PyTorch and JAX and their system architectures.
• Experience or interest in reinforcement learning workloads and distributed training frameworks.
• Ability to collaborate across teams and take initiative in cross-stack projects.

Nice to have

• Experience training or supporting large-scale language models with tens of billions of parameters.
• Background in high-performance or reliability engineering, cluster orchestration (Kubernetes, Slurm).
• Familiarity with monitoring tools like Prometheus, Grafana, OpenTelemetry.
• Contributions to large-scale ML research, open-source frameworks, or performance optimization.

Culture & Benefits

• Visa sponsorship and relocation support available.
• Generous health, dental, and vision benefits.
• Unlimited paid time off and paid parental leave.
• Collaborative environment with cross-functional teams.