Job Overview
Location
San Francisco
Job Type
Full-time
Category
Embedded Engineer
Date Posted
March 23, 2026
Full Job Description
đź“‹ Description
- • As a Hardware/Software CoDesign Engineer at OpenAI, you will play a pivotal role in shaping the future of AI infrastructure by bridging the gap between cutting-edge hardware design and software optimization for large-scale AI workloads. Your work will directly influence the performance, efficiency, and scalability of OpenAI’s next-generation AI supercomputing systems, ensuring that hardware innovations are tightly aligned with the evolving demands of large language models and other advanced AI techniques.
- • You will collaborate with cross-functional teams of machine learning researchers, kernel engineers, compiler developers, and external hardware vendors to co-design accelerators and system architectures that maximize throughput, minimize latency, and optimize energy efficiency for training and inference at scale. This role sits at the forefront of AI infrastructure innovation, where your contributions will help define how future AI models are deployed across global supercomputing fleets.
- • Day to day, you will: co-design future hardware architectures with vendors to enhance programmability and performance for AI workloads; assist hardware partners in developing and integrating optimized kernels into OpenAI’s compiler stack; develop performance models and estimates for critical kernels across diverse hardware configurations to guide decisions on compute core design, memory hierarchy, and interconnect topology; build and analyze system-level performance models at multiple abstraction levels to inform scale-up, scale-out, and networking strategies for datacenter racks and facilities; work closely with ML, kernel, and compiler engineers to translate their algorithmic and numerical needs into hardware requirements; manage technical communication and coordination with internal teams and external partners to ensure alignment on roadmaps and deliverables; influence the product roadmaps of hardware vendors by advocating for features that optimize OpenAI’s specific workloads; evaluate emerging accelerator platforms and architectures for potential integration into OpenAI’s infrastructure; and, as the team scales, contribute to shaping hardware strategies for datacenter-level systems including network fabrics, rack designs, and facility-level power and cooling considerations.
- • You will join a world-class hardware organization within OpenAI that is dedicated to building AI-native silicon and system solutions from the ground up. This team operates at the intersection of systems architecture, compiler technology, and machine learning, fostering a deeply collaborative environment where hardware and software co-design is not just a practice but a core philosophy. You will work alongside experts who have pushed the boundaries of AI infrastructure at companies like Google, NVIDIA, and leading semiconductor firms, all united by the mission to make advanced AI accessible, efficient, and safe.
- • In this role, you will gain deep expertise in the full stack of AI infrastructure — from transistor-level architecture to large-scale distributed training systems. You will develop rare, high-impact skills in hardware-software co-design, performance modeling for ML workloads, accelerator programming (CUDA, Triton), and low-precision numerical methods. You will have the opportunity to publish insights, influence industry standards through vendor engagements, and see your contributions deployed in some of the largest AI supercomputers in the world. This is a unique chance to grow as a technical leader in one of the most consequential and rapidly evolving fields in technology.
🎯 Requirements
- • 4+ years of industry experience in hardware/software co-design, with proven experience optimizing ML platform code for efficient execution on target hardware such as GPUs or AI accelerators
- • Strong proficiency in C/C++ and Python, along with hands-on experience in accelerator programming languages including CUDA, Triton, or similar frameworks
- • Deep understanding of GPU architecture, AI accelerator design, and the fundamentals of deep learning computing, including memory hierarchy, parallelism, and numerical approximation techniques
- • Experience driving machine learning accuracy using low-precision formats (e.g., FP8, INT8) and applying system performance modeling and analysis to optimize ML model deployment across hardware configurations
🏖️ Benefits
- • Hybrid work model with 3 days in the office per week in San Francisco, offering flexibility and collaboration
- • Relocation assistance provided for new employees transitioning to the San Francisco Bay Area
- • Access to OpenAI’s cutting-edge AI research environment, including opportunities to work with state-of-the-art models and infrastructure
- • Comprehensive health, wellness, and financial benefits package aligned with OpenAI’s commitment to employee well-being
- • Opportunity to work on mission-critical AI infrastructure with global impact, surrounded by world-class researchers and engineers
Skills & Technologies
Python
Hybrid
Degree Required
About OpenAI, Inc.
OpenAI is a San Francisco-based artificial intelligence research and deployment company founded in 2015. It develops large-scale AI models such as GPT, DALL-E, and Codex, providing cloud APIs and consumer applications like ChatGPT. Originally established as a non-profit, it later created a capped-profit subsidiary to attract capital while maintaining its mission to ensure artificial general intelligence benefits all of humanity.
Get more remote jobs like this
Subscribe to the weekly newsletter for similar remote roles and curated hiring updates.
Newsletter
Weekly remote jobs and featured talent.
No spam. Only curated remote roles and product updates. You can unsubscribe anytime.
Similar Opportunities
❌ EXPIRED
Lytx, Inc.
Remote - Israel
Full-time
Expired Mar 17, 2026
Go
Linux
Senior
+1 more
3 months ago
