Senior Systems Software Engineer - Deep Learning Solutions

What you'll do

• Analyze, debug, and optimize customer deep learning workloads on NVIDIA platforms; deliver production-ready solutions.
• Lead reproducible performance benchmarking and evaluate emerging model architectures for compilation feasibility, memory use, and latency.
• Build and deploy edge inference solutions on Jetson, DRIVE, and GPU + ARM platforms, collaborating with compiler, runtime, and hardware teams.

What they ask for

• Master’s degree or equivalent experience in Computer Science, Electrical Engineering, or a related field.
• Over 12 years working in the industry, including at least 8 years specializing in deep learning model optimization, inference engineering, or neural network compilation.
• Over 5 years of validated expertise in embedded/edge software and production inference for power-limited, latency-sensitive environments.
• Expert knowledge of GPU architecture fundamentals, CUDA, low-level performance optimization, and TensorRT, compiler IRs, or equivalent inference optimization toolchains.

Nice to have

• Experience with ML compiler frameworks (TVM, MLIR, XLA, Triton) or inference runtime development.
• Production autonomous vehicle perception or planning deployment experience; MLPerf contributions and automotive safety standards familiarity are also noted as advantages.

Pay

224,000 USD - 356,500 USD (base salary)

Tools

CUDA, TensorRT, Torch-TRT, MLIR-TRT, Jetson, DRIVE, GPU + ARM, QNX/Linux

AI focus

Deep learning inference optimization and deployment for autonomous vehicles and robotics, including evaluation of transformers, vision-language models, diffusion/flow matching models, and state space models.