RTL Design Engineer, Networking / NoC

OpenAI•San Francisco, CA
•$287,000 - $485,000

About The Position

OpenAI’s Hardware organization develops AI-native silicon and system-level solutions for advanced AI workloads. The team is developing future generations of AI-native silicon and tightly integrated systems for OpenAI’s supercomputing platform. The RTL Design Engineer will help design and develop next-generation AI accelerator silicon, working across architecture, microarchitecture, and RTL implementation to translate system and performance requirements into efficient, scalable hardware. The role involves close collaboration with silicon architects, hardware and software engineers, verification teams, and physical design teams. It includes opportunities to influence architectural decisions, develop microarchitecture, and own RTL design from early concept through implementation and integration. Experience with Network-on-Chip (NoC), networking, interconnect architectures, or high-performance data movement is of particular interest, alongside broader RTL design and hardware co-design experience.

Requirements

  • Strong hands-on experience with ASIC RTL design and microarchitecture development using SystemVerilog or Verilog.
  • Experience designing and implementing complex digital hardware blocks, from architecture and specification through RTL development and verification.
  • Understanding of hardware architecture and microarchitecture tradeoffs, including performance, power, area, latency, and throughput.
  • Experience collaborating across architecture, software, verification, and physical design teams to develop optimized hardware solutions.
  • Ability to reason about complex hardware systems, identify performance bottlenecks, and translate architectural requirements into efficient RTL implementations.
  • Experience with synthesis, timing closure, and physical implementation considerations.
  • Ability to take ownership of designs from concept through integration and work on ambiguous, technically challenging problems.

Nice To Haves

  • Experience with Network-on-Chip (NoC), networking, interconnect fabrics, packet-based architectures, or high-bandwidth data movement systems.
  • Experience with AI accelerators, high-performance computing, or hardware/software co-design.

Responsibilities

  • Design and implement high-performance RTL for next-generation AI accelerator silicon, from microarchitecture definition through implementation and integration.
  • Collaborate with architecture and software teams to translate system-level requirements into efficient hardware microarchitectures.
  • Drive hardware/software co-design efforts to optimize performance, power, area, and scalability for AI workloads.
  • Develop and optimize RTL for complex datapaths, control logic, interconnects, and other critical silicon subsystems.
  • Evaluate architectural and microarchitectural tradeoffs across bandwidth, latency, throughput, and resource utilization.
  • Partner with design verification and formal verification teams to ensure functional correctness, develop verification strategies, and debug complex design issues.
  • Work with physical design teams to optimize RTL for synthesis, timing closure, power, and area.
  • Contribute to architecture reviews, design specifications, and cross-functional discussions to influence future silicon designs.
  • Support block-level and SoC-level integration, debugging, and performance optimization.
© 2026 Teal Labs, Inc
Privacy PolicyTerms of Service