Staff AI Inference and Acceleration Engineer
$180k - $275k • San Jose, CA
Posted 9d ago
About the job
Figure is an AI robotics company developing autonomous general-purpose humanoid robots with the goal of shipping robots with human-level intelligence. These robots are engineered to perform a variety of tasks in home and commercial markets. We are seeking a Staff AI Inference & Acceleration Engineer to join our Platform Software team. This role will be responsible for the on-board inference architecture for our humanoid robots, acting as the technical authority on how AI workloads are mapped, optimized, and executed across the robot's compute hardware. The primary objective is to reduce power consumption and cost while meeting strict latency and reliability demands for a real-time autonomous system.
Responsibilities
- Own the on-board inference architecture, mapping models to accelerators based on latency, power, and memory budgets.
- Partition inference workloads across heterogeneous compute resources, balancing performance with power and thermal constraints.
- Define and maintain a system-level compute budget for all inference tasks.
- Evaluate next-generation acceleration hardware and contribute to future compute platform requirements.
- Optimize inference toolchains end-to-end for target hardware.
- Apply quantization, pruning, and other compression techniques to reduce compute, memory, and power footprint.
- Profile inference pipelines to identify and eliminate bottlenecks.
- Optimize kernel scheduling, memory layout, and data movement.
- Partner with the AI/ML team to define hardware-friendly model architecture constraints.
- Work with the Platform Software team on runtime integration, scheduling, and power management.
- Engage with silicon vendors and research teams to track the accelerator landscape and influence hardware roadmaps.
Requirements
- M.S. or Ph.D. in Computer Engineering, Electrical Engineering, Computer Science, or equivalent industry experience.
- At least 8 years of industry experience in hardware acceleration, ML systems, or compute architecture.
- Deep understanding of AI/ML inference, including model formats, inference runtimes, and deployment pipelines.
- Hands-on experience optimizing models for edge or embedded hardware using quantization, pruning, and operator-level tuning.
- Strong understanding of computer architecture, including memory hierarchies, data movement, and heterogeneous compute.
- Experience profiling and benchmarking inference workloads across CPU, GPU, NPU, DSP.
- Familiarity with low-level toolchains and compilation frameworks (e.g., TVM, MLIR, TensorRT, Torch, SNPE/QNN, JAX, CUDA, ROCm).
- Solid software engineering skills in C++ and Python.
- Strong cross-functional communication skills.