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
CUDA @ 4
Deep Learning @ 7
Docker @ 3
GPU @ 4
LLM @ 4
PyTorch @ 7
Python @ 7
SGLang @ 4
TensorRT @ 4
vLLM @ 4
- 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.
Details
We are looking for a Senior Deep Learning Engineer to help bring Cosmos World Foundation Models from research into efficient, production-grade systems. You will focus on optimizing and deploying models for high-performance inference on diverse GPU platforms. This role sits at the intersection of deep learning, systems, and GPU optimization, working closely with research scientists, software engineers, and hardware experts.
NVIDIA Cosmos is a platform purpose-built for physical AI, featuring powerful generative models. Developers use Cosmos to accelerate physical AI development for autonomous vehicles, robots, and video analytics AI agents by simulating and reasoning about the physical world.
Responsibilities
- Improve inference speed for Cosmos World Foundation Models on GPU platforms.
- Effectively carry out the production deployment of Cosmos World Foundation Models.
- Profile and analyze deep learning workloads to identify and remove bottlenecks.
Requirements
- 5+ years of experience.
- MSc or PhD in Computer Science, Electrical Engineering, Computer Science and Engineering, or equivalent experience.
- Strong background in deep learning.
- Strong programming skills in Python and PyTorch.
- Experience with inference optimization techniques, such as quantization, and inference optimization frameworks including TensorRT, TensorRT-LLM, vLLM, or SGLang.
Preferred Qualifications
- Familiarity with deploying deep learning models in production settings, such as Docker and Triton Inference Server.
- CUDA programming experience.
- Familiarity with diffusion models.
- Proven experience analyzing, modeling, and tuning the performance of GPU workloads for both inference and training.
Compensation
For Poland, the base salary range is 221,250 PLN–383,500 PLN for Level 3 and 292,500 PLN–507,000 PLN for Level 4. Base salary is determined based on location, experience, and the pay of employees in similar positions.