Senior / Staff AI Research Engineer, Real-Time Inference (AI)

Location: Milpitas, California, United States; 5 days/week in-office collaboration required

Salary: $185,000–$325,000 USD base salary per year, plus bonus and equity.

Company

hirify.global is an AI robotics company developing Physical AI-powered robots for dull, dirty, and dangerous industrial work, with a focus on real-world deployment and scalability.

What you will do

• Develop and optimize real-time inference pipelines for embodied AI models, including VLA, perception, and world models, on NVIDIA Jetson and other edge platforms.
• Implement CUDA custom kernels, memory-layout tuning, and hardware-aware graph compilation to reduce model latency.
• Apply quantization, pruning, distillation, and structured sparsity to achieve production-grade throughput on constrained devices.
• Profile and debug inference stacks with Nsight, TensorRT, and Triton, identifying and removing performance bottlenecks.
• Collaborate with ML research and robotics teams to co-design models meeting real-time control-loop latency requirements.
• Build benchmarking frameworks covering latency, throughput, power consumption, and accuracy trade-offs on target hardware.

Requirements

• Master’s degree in Computer Science, Electrical Engineering, or a related field with 4+ years of experience, or a PhD.
• Deep expertise in CUDA programming, GPU architecture, low-level kernel optimization, and custom kernel authoring with tools such as Triton.
• Hands-on experience with model quantization, pruning, distillation, and deployment using TensorRT, ONNX Runtime, TVM, or Triton.
• Proficiency in C++ and Python, with strong systems programming and performance profiling skills.
• Experience deploying ML models on edge or embedded hardware such as NVIDIA Jetson, Orin, or equivalent ARM/GPU SoCs.
• Availability for 5 days/week of in-office collaboration is required.

Nice to have

• Familiarity with embodied AI models, including VLA, multimodal transformers, or diffusion-based policies, and their inference characteristics.
• Familiarity with compiler-based optimization pipelines such as XLA, torch.compile, or MLIR.
• Understanding of robotics constraints such as control-loop timing, sensor-fusion latency, and memory-bandwidth limits on edge SoCs.
• Publications or production experience in efficient deep learning or on-device ML systems.

Culture & Benefits

• Full-time U.S. position with compensation determined by role scope, level, location, skills, experience, and education; exceptional cases may fall outside the listed salary range.
• Competitive stock options or equity programs, plus a bonus.
• Health, dental, and vision insurance and a 401(k) plan.
• Visa sponsorship and green card support are available for qualified candidates.
• Lunches and dinners, a stocked kitchen, and regular team-building events.