Software Engineer, Kernel Performance & AI Tooling
Remote • San Francisco • FullTime
Posted 5mo ago
Remote Work Policy
Fully remote
Employment Type
FullTime
Categories
Applied AI Engineer
About the job
OpenAI's Hardware organization is developing AI-native silicon and system-level solutions for advanced AI workloads. We are seeking a systems-minded engineer to advance our kernel development, performance engineering, and hardware-software co-design capabilities, with a focus on AI-assisted workflows and tooling. This role sits at the intersection of kernel optimization, developer tooling, observability, and research infrastructure, aiming to improve how production kernels are built and optimized, and how future hardware-software systems are designed and evaluated. The ideal candidate is excited by low-level performance work and sees AI and automation as powerful tools for accelerating engineering velocity, helping to define the future of kernel engineering in the era of AI-assisted development.
Responsibilities
- Build developer tooling and workflows to accelerate kernel development and performance optimization.
- Develop observability, diagnostics, and validation infrastructure for AI-assisted optimization systems.
- Optimize production kernels end-to-end, including problem formulation, search loops, bottleneck analysis, and debugging.
- Design abstractions, interfaces, and automation systems for kernel optimization and hardware-software co-design.
- Improve AI-assisted optimization systems through better datasets, evaluations, and research infrastructure.
- Partner with research and engineering teams to translate new ideas into practical systems.
Requirements
- Strong systems or tooling engineering experience with a background in low-level software, performance optimization, or infrastructure.
- Experience with developer tooling, debugging infrastructure, profiling, observability, or workflow design.
- Depth in kernel development, accelerator architecture, compiler systems, or related performance-critical domains.
- Familiarity with AI-assisted systems, agentic workflows, post-training, or reinforcement learning for engineering or research.
- Strong experimental judgment, comfort with ambiguity, and ability to move between research and production.
- Interest in compilers, DSLs, program synthesis, or AI for systems.
- Hands-on experience optimizing code for GPUs, high-performance CPUs, or custom accelerators.