Senior Edge AI Research Engineer — Real-Time Inference

RoboForce; Milpitas (CA); On-site; USD 185,000 - 325,000; Full time

Benefits offered by this job

Stock options/equity

Health, dental, and vision insurance

401(k) plan

Visa sponsorship

Green card support

Meals provided (lunches/dinners)

Job summary

RoboForce in Milpitas, CA is seeking a Senior / Staff AI Research Engineer to enable embodied AI on the edge. You will optimize inference pipelines and implement CUDA kernels to deploy high-performance models on edge compute platforms powering RoboForce robots.

You will drive model compression and hardware-aware graph compilation, profiling with NSight and TensorRT, and collaborate with ML research and robotics teams to meet strict real-time latency requirements.

Qualifications

• MS/PhD in CS/EE or related field with 4+ years of experience.
• Deep CUDA programming, GPU architecture, and low-level kernel optimization.
• Hands-on deployment of models on edge hardware (NVIDIA Jetson/Orin).
• Strong proficiency in C++ and Python; performance profiling.
• Experience with TensorRT, ONNX Runtime, TVM, or Triton.

Responsibilities

• Develop and optimize real-time inference pipelines for embodied AI models on edge hardware.
• Implement CUDA-level optimizations, custom kernels, memory layout tuning.
• Apply model compression: quantization, pruning, distillation, sparsity.
• Profile and debug inference stacks with NSight, TensorRT, Triton.
• Collaborate with ML research and robotics teams on model architectures.
• Establish benchmarks for latency, throughput, power, accuracy on target hardware.

Skills

CUDA programming

GPU architecture

C++

Python

Performance profiling

Edge deployment

Quantization/Pruning

Model compression

Embedded systems

Education

MS/PhD in CS/EE

Tools

TensorRT

ONNX Runtime

TVM

Triton

NSight

Job description

RoboForce in Milpitas, CA is seeking a Senior / Staff AI Research Engineer to enable embodied AI on the edge. You will optimize inference pipelines and implement CUDA kernels to deploy high-performance models on edge compute platforms powering RoboForce robots.

You will drive model compression and hardware-aware graph compilation, profiling with NSight and TensorRT, and collaborate with ML research and robotics teams to meet strict real-time latency requirements.