Senior Research Engineer: Generative AI Inference (Remote)

NVIDIA Corporation; Santa Clara (CA); On-site; USD 192,000 - 356,500; Full time

Benefits offered by this job

Equity

Benefits

Job summary

NVIDIA Corporation in the United States (CA/Santa Clara) is seeking a Senior Research Engineer focused on Generative AI inference to design LLM routing and benchmarking policies. You will collaborate across the NVIDIA stack and ship design docs, code, and community contributions.

Preferred candidates hold a CS degree with 8+ years in deep learning, ML/NLP expertise, and an empirical research mindset; mentoring and strong communication are valued. Equity and benefits apply to eligible employees.

Qualifications

• Bachelor's or Master's in CS or equivalent experience.
• 8+ years in deep learning frameworks (PyTorch / TensorFlow).
• Experience with LLM evaluations/benchmarks and statistics.
• Strong ML/NLP knowledge with empirical research mindset.

Responsibilities

• Design routing policies for LLM traffic to optimize model usage.
• Build agentic benchmarks and turn results into calibration data.
• Collaborate with NVIDIA teams to integrate software across the stack.
• Mentor junior engineers and contribute to open-source docs.

Skills

DL frameworks

LLM benchmarks

Distributed systems

CUDA GPU programming

CS fundamentals

Mentoring

Communication

Education

Bachelor's or Master's in CS or equivalent experience

Job description

NVIDIA Corporation in the United States (CA/Santa Clara) is seeking a Senior Research Engineer focused on Generative AI inference to design LLM routing and benchmarking policies. You will collaborate across the NVIDIA stack and ship design docs, code, and community contributions.

Preferred candidates hold a CS degree with 8+ years in deep learning, ML/NLP expertise, and an empirical research mindset; mentoring and strong communication are valued. Equity and benefits apply to eligible employees.