Senior Deep Learning Algorithm Engineer

at Nvidia

USD 152,000-287,500 per year

SENIOR

✅ Hybrid

Tech Stack
Tag name is followed by "@" symbol and proficiency level value. About proficiency levels:

1-2 — basic awareness. Minimal hands-on experience, and a rudimentary understanding of the technology's purpose;

3-6 — daily use. Comfortable and regular usage, capable of handling common tasks and challenges related to the technology;

7-9 — you are an expert, you can teach others, you know all the pitfalls and tricks;

10 — exceptional knowledge, comprehensive understanding, and adeptness in all aspects of the technology, including advanced problem-solving. Think twice before claiming or demanding such level.

AI @ 4 Algorithms Debugging @ 6 Deep Learning Distributed Systems @ 6 LLM Leadership @ 6 Machine Learning @ 6 Networking Profiling @ 6 Python @ 7 Rust @ 7 SGLang TensorRT vLLM

Details

NVIDIA is seeking a Senior Deep Learning Algorithms Engineer to advance Dynamo, its open-source distributed inference platform for large-scale, low-latency AI services. You will lead architecture and performance work across Dynamo and open-source frameworks, collaborating with research, software, systems, and hardware teams to make AI inference faster, more efficient, and easier to deploy. You will engage with the broader ecosystem, including vLLM, SGLang, and TensorRT-LLM, as well as external partners.

Responsibilities

Design, build, and maintain Dynamo integrations for the open-source frameworks vLLM, SGLang, and TensorRT-LLM.
Partner with open-source communities to achieve measurable gains in latency, throughput, reliability, and efficiency.
Showcase NVIDIA token-per-watt leadership by pushing the Pareto frontier on public and private benchmarks.
Find and remove bottlenecks across runtimes, kernels, networking, routing, and orchestration.
Develop inference optimizations for scheduling, disaggregation, KV caching, and autoscaling.

Requirements

Bachelor's, master's, or doctoral degree in Computer Science, Electrical Engineering, Computer Engineering, or a related field, or equivalent experience.
At least 3 years of experience building, profiling, and debugging performance-critical distributed or machine learning systems.
Strong programming skills in Python and/or Rust and C++.
Understanding of modern machine learning architectures and inference techniques.

Preferred Qualifications

High agency and a track record of leading ambiguous work end to end.
Experience with AI accelerators.
Open-source contributions or leadership.
Research experience in machine learning inference or distributed systems.

Benefits

The role includes eligibility for equity and NVIDIA benefits. NVIDIA is an equal opportunity employer committed to fostering an inclusive work environment.