NVIDIA

4 days ago

Senior Software Engineer - GPU Local AI Platforms

✓ Verified Job

Canonical indexed version, validated from employer's careers page.

Source: Company careers pageValidated by: Fursa AI

Last checked: 13 hours agoStatus: Live

Job Summary

Build and optimize NVIDIA’s Local AI software stack for running large language models efficiently on edge AI hardware. You’ll track open-source inference frameworks, map model architectures and algorithms to GPU architecture, analyze multi-node inference performance, and produce validation workflows and developer-facing inference recipes that stay current as frameworks evolve.

Location: Santa Clara, Austin, Durham, Seattle

Workplace: Onsite

Employment Type: Full time

Job Function: Software Engineering

Seniority: Mid level

Key Responsibilities

•Evaluate and track innovations in open-source LLM inference frameworks and identify performance-critical features for NVIDIA edge AI hardware.
•Analyze how new model architectures and inference algorithms map to NVIDIA GPU architecture, identifying optimization opportunities and fallback paths.
•Characterize multi-node inference behavior, including NCCL/RCCL primitives, topology-aware all-reduce strategies, and parallelism efficiency.
•Produce performance analysis reports tying theoretical hardware limits to observed throughput, latency, and utilization.
•Own model validation and developer inference recipe workflows for new model releases, including architecture compatibility assessment and performance characterization.

Pay and Benefits

Salary: USD 224,000 - 431,250 annually

Equity and Bonus:Equity

Key Requirements

•12+ years of software engineering with depth in GPU computing, ML systems, or high-performance inference.
•BS, MS, or PhD in Computer Science, Computer Engineering, Electrical Engineering, or equivalent experience.
•Strong Python or C++ programming, software design, and software engineering skills.
•Hands-on GPU kernel development or optimization (CUDA/C++, Triton, or equivalent), including understanding of thread blocks and warp execution.
•Working knowledge of LLM inference internals such as attention mechanisms, KV-cache management, continuous batching, quantization formats, and tensor parallelism.

Experience:12+ yearsGPU computingML systemsHigh-performance inferenceOpen-sourceLLM inference

Education:Bachelor's in Computer Science, Computer Engineering, Electrical Engineering

Skills:Strong analytical skillsAbility to form hypothesesExperiment designClear communication

Tech Stack:PythonC++CUDATritonDockerOCINVIDIA Container ToolkitNCCLRCCLCI/CDQuantizationKV-cacheTensor parallelismContinuous batching

Company Brief

NVIDIA

Designs and manufactures GPUs, AI accelerators, and system-on-chip products for gaming, data centers, professional visualization, and automotive markets, enabling advanced graphics, AI, and high-performance computing solutions worldwide.

Industry: Electronics Manufacturing

Company Size: Enterprise (1,001+ employees)

Revenue: USD 1B+

Growth: Public Company

Valuation: Public Company (Market Cap in USD)

Funding: IPO / Publicly Listed

Headquarters: Santa Clara, United States

Founded: 1993

Glassdoor: 4.3

Website LinkedIn Glassdoor

Loading job details...

Preparing the role view and application actions.

NVIDIA

4 days ago

Senior Software Engineer - GPU Local AI Platforms

✓ Verified Job

Canonical indexed version, validated from employer's careers page.

Source: Company careers pageValidated by: Fursa AI

Last checked: 13 hours agoStatus: Live

Job Summary

Location: Santa Clara, Austin, Durham, Seattle

Workplace: Onsite

Employment Type: Full time

Job Function: Software Engineering

Seniority: Mid level

Key Responsibilities

•Evaluate and track innovations in open-source LLM inference frameworks and identify performance-critical features for NVIDIA edge AI hardware.
•Analyze how new model architectures and inference algorithms map to NVIDIA GPU architecture, identifying optimization opportunities and fallback paths.
•Characterize multi-node inference behavior, including NCCL/RCCL primitives, topology-aware all-reduce strategies, and parallelism efficiency.
•Produce performance analysis reports tying theoretical hardware limits to observed throughput, latency, and utilization.
•Own model validation and developer inference recipe workflows for new model releases, including architecture compatibility assessment and performance characterization.

Pay and Benefits

Salary: USD 224,000 - 431,250 annually

Equity and Bonus:Equity

Key Requirements

•12+ years of software engineering with depth in GPU computing, ML systems, or high-performance inference.
•BS, MS, or PhD in Computer Science, Computer Engineering, Electrical Engineering, or equivalent experience.
•Strong Python or C++ programming, software design, and software engineering skills.
•Hands-on GPU kernel development or optimization (CUDA/C++, Triton, or equivalent), including understanding of thread blocks and warp execution.
•Working knowledge of LLM inference internals such as attention mechanisms, KV-cache management, continuous batching, quantization formats, and tensor parallelism.

Experience:12+ yearsGPU computingML systemsHigh-performance inferenceOpen-sourceLLM inference

Education:Bachelor's in Computer Science, Computer Engineering, Electrical Engineering

Skills:Strong analytical skillsAbility to form hypothesesExperiment designClear communication

Tech Stack:PythonC++CUDATritonDockerOCINVIDIA Container ToolkitNCCLRCCLCI/CDQuantizationKV-cacheTensor parallelismContinuous batching

Company Brief

NVIDIA

Industry: Electronics Manufacturing

Company Size: Enterprise (1,001+ employees)

Revenue: USD 1B+

Growth: Public Company

Valuation: Public Company (Market Cap in USD)

Funding: IPO / Publicly Listed

Headquarters: Santa Clara, United States

Founded: 1993

Glassdoor: 4.3

Website LinkedIn Glassdoor