$220,920 - $361,480 USD yearly
Originally posted August 29, 2026 by the employer.
About the role
This role involves serving as a systems architect for humanoid robots, owning the end-to-end hierarchical stack. It focuses on the co-optimization of large vision-language-action (VLA) models with compute silicon under tight power, thermal, latency, and memory-bandwidth constraints.
What you'll do
- Own the hierarchical control stack, including VLM/VLA systems, visuomotor policies, and distributed joint FOC loops.
- Define hierarchical multi-system architecture requirements and select interconnect topologies like EtherCAT.
- Drive co-optimization of large VLA/world models with compute silicon by defining quantization, sparsity/MoE, and context lengths.
- Perform first-principles sizing of FLOPs, sustained TOPS, and memory-bandwidth floors.
- Author and maintain primary system-level specifications for compute, power, thermal, sensors, and actuator networks.
- Lead multi-disciplinary architecture reviews and subsystem design trades across ML research, controls, electrical, firmware, and mechanical teams.
What you'll need
- 10+ years in complex cyber-physical systems.
- 4-5 years specializing in robotics, autonomous systems, or high-performance edge AI platforms.
- BS in Engineering, Computer Science, Math, or a related field.
- Proven ownership of architectures bridging high-level AI models with real-time hardware control.
- Deep fluency in transformer inference constraints (quantization, action chunking, memory bandwidth walls) and real-time distributed systems (EtherCAT, zonal sensor pods, safety islands).
Nice to have
- Direct experience with humanoid robots/mobile manipulators.
- Hands-on exposure to VLA/foundation models (e.g., -series, Helix-class, GR00T, OpenVLA).
- Expertise with robotics platforms (NVIDIA Jetson / IGX platforms, custom AI silicon).
- Experience with battery/thermal budgeting for highly constrained systems.
Skills: humanoid robotics, VLA models, compute silicon, system architecture, memory-bandwidth, EtherCAT
More semiconductor jobs: Intel Corporation jobs · AI chip design jobs
Tracked in our index since 29 Aug 2026. This is our observation date, not the employer posting date. Specialty: AI/ML Hardware Engineering (AI ML Hardware). 480 active roles in this specialty at 76 employers in our index, as of 18 Nov 2026.
How we counted: postings read from employer career sites. How we count