Senior / Staff 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

Senior / Staff AI Research Engineer, Real-Time Inference

Milpitas, CA

Why RoboForce

RoboForce is an AI robotics company developing Physical AI–powered Robo-Labor for dull, dirty, and dangerous work. The company's robots are engineered for demanding industrial environments, with a focus on real-world deployment and scalability.

We are looking for a Senior / Staff AI Research Engineer, Real-Time Inference to make embodied AI practical on the edge. In this role, you will drive the full stack of model optimization — from CUDA kernel engineering to quantization and compression — to deploy high-performance AI models on edge compute platforms powering RoboForce robots in the field.

Responsibilities

Develop and optimize inference pipelines for embodied AI models (VLA, perception, world models) targeting real-time execution on edge hardware such as NVIDIA Jetson platforms.

Implement CUDA-level optimizations including custom kernels, memory layout tuning, and hardware-aware graph compilation to minimize model latency.

Apply and advance model compression techniques — quantization (INT8/FP16/INT4), pruning, distillation, and structured sparsity — to achieve production-grade throughput on constrained devices.

Profile and debug end-to-end inference stacks using tools such as NSight, TensorRT, and Triton to identify and eliminate performance bottlenecks.

Collaborate with ML research and robotics teams to co-design model architectures that meet real-time control-loop latency requirements.

Establish benchmarking frameworks to evaluate model performance across latency, throughput, power consumption, and accuracy tradeoffs on target hardware.

Requirements

Master's degree in Computer Science, Electrical Engineering, or related field with 4+ years of experience, or a PhD degree.

Deep expertise in CUDA programming, GPU architecture, and low-level kernel optimization, including custom kernel authoring with tools such as Triton.

Hands-on experience with model quantization, pruning, distillation, and deployment using frameworks such as TensorRT, ONNX Runtime, TVM, or Triton.

Proficiency in C++ and Python; strong systems programming and performance profiling skills.

Experience deploying ML models on edge or embedded hardware (e.g., NVIDIA Jetson, Orin, or equivalent ARM/GPU SoCs).

Requires 5 days/week in-office collaboration with the teams.

Bonus Qualifications

Familiarity with embodied AI models — VLA, multimodal transformers, or diffusion-based policies — and their inference characteristics.

Familiarity with compiler-based optimization pipelines such as XLA, torch.compile, or MLIR for graph-level model acceleration.

Understanding of robotics system constraints such as control-loop timing, sensor fusion latency, and memory bandwidth limits on edge SoCs.

Publication or production work in efficient deep learning or on-device ML systems.

Competitive stock options/equity programs.

Health, dental, and vision insurance, 401(k) plan.

Visa sponsorship and green card support for qualified candidates.

Lunches and dinners, a fully stocked kitchen, and regular team-building events.

Compensation: Salary $185,000–$325,000 USD + Bonus + Equity

The base salary range above represents the expected compensation for this full-time U.S. position. Final compensation will be determined based on role scope, level, location, job‑related skills, experience, and relevant education or training, and may fall outside the listed range in exceptional cases.