Software Engineer, Distributed Systems at OpenAI - San Francisco, CA

Join OpenAI's Compute Runtime team building the foundational infrastructure powering the world's most advanced ML training systems. As a Software Engineer specializing in Distributed Systems, you'll architect the low-level frameworks that orchestrate thousands of computers moving petabytes of training data across our cutting-edge supercomputers.

This hybrid role in San Francisco offers relocation assistance and combines the excitement of AGI research with hands-on systems engineering at exascale. If you thrive on optimizing end-to-end performance while maintaining developer-friendly APIs, this is your opportunity to accelerate humanity's progress toward artificial general intelligence.

Key Responsibilities

• Architect powerful, introspectable APIs orchestrating thousands of GPUs and CPUs for seamless data movement and persistence across distributed clusters
• Profile and optimize high-performance I/O pipelines maximizing local storage throughput and network fabric utilization
• Design scalable compute runtime components supporting dynamic ML training workloads from research prototypes to production supercomputers
• Rapidly deploy training frameworks to bleeding-edge hardware architectures responding to evolving model requirements
• Build robust Python and Rust components ensuring stability when scaling from hundreds to tens of thousands of nodes
• Collaborate with ML researchers to understand data movement patterns and optimize for researcher productivity
• Implement observability and monitoring systems providing real-time insights into cluster-wide performance bottlenecks
• Create fault-tolerant designs automatically recovering from hardware failures across massive distributed systems
• Optimize end-to-end training stack minimizing job completion times while maintaining system reliability
• Develop debugging tools enabling rapid iteration cycles even at supercomputer scale
• Contribute to open-source components advancing the state of distributed ML infrastructure
• Mentor junior engineers while leading critical infrastructure initiatives

Qualifications & Requirements

Technical Expertise:

• 5+ years experience building production distributed systems handling massive scale
• Deep proficiency in Python and Rust (or C++/Go) for systems programming
• Proven track record profiling/optimizing I/O-bound and compute-bound workloads
• Hands-on experience deploying to GPU clusters or supercomputing environments

Mindset & Approach:

• Obsessive focus on end-to-end system performance and developer experience
• Thrives in ambiguity with rapidly changing requirements and hardware stacks
• Natural instinct for simplifying complex systems without sacrificing capability
• Strong ownership mentality delivering reliable systems at exascale

Bonus Points:

• Experience with ML training infrastructure (PyTorch, JAX, etc.)
• Supercomputing center experience (LLNL, NERSC, etc.)
• Contributions to distributed systems frameworks (Ray, Dask, etc.)

Salary & Benefits

Compensation: $250,000 - $450,000 base + equity + benefits (San Francisco market rate)

Comprehensive Benefits Package:

• Top-tier medical, dental, vision coverage with low employee premiums
• 401(k) with 4%+ employer match
• Unlimited PTO with wellness days
• 16 weeks paid parental leave (primary/secondary caregivers)
• $2,000+ annual learning stipend
• Fitness reimbursement up to $100/month
• Daily catered meals in SF office
• Relocation package including housing and moving support
• Commuter benefits and subsidized housing options

Hybrid schedule: 3 days/week in our state-of-the-art San Francisco headquarters.

Why Join OpenAI?

OpenAI isn't just building AI products—we're creating the infrastructure that makes AGI possible. Our Compute Runtime team sits at the foundation, enabling researchers to push boundaries without infrastructure bottlenecks.

Impact at Scale: Your optimizations directly accelerate humanity's path to AGI

Cutting-Edge Challenges: Work with hardware and scale most engineers never see

Research Synergy: Partner directly with world-class ML researchers

Team Culture: Collaborative, mission-driven engineers who move fast and ship reliable systems

How to Apply

Submit your resume and a brief note explaining why you're excited about distributed systems at OpenAI scale. Tell us about your favorite optimization you've implemented and the impact it had.

Timeline: Rolling applications with interviews typically within 1-2 weeks

Process: Technical screen → Systems coding → Distributed systems deep dive → Team match

Apply Now