Senior Deep Learning Software Engineer, Inference

This is a fully remote position, open to applicants in Poland, +2 more countries.

📋 Description

• Design, construct, and enhance GPU-accelerated software tailored for AI applications.

• Develop and sustain high-performance deep learning frameworks such as SGLang and vLLM.

• Enhance platforms to streamline the deployment and serving of language models.

• Integrate the latest algorithms for public release within SGLang, vLLM, and other deep learning frameworks.

• Recognize and drive performance enhancements for cutting-edge LLM and Generative AI models utilizing NVIDIA accelerators.

• Utilize open-source tools and plugins, including CUTLASS, OAI Triton, NCCL, and CUDA kernels, to implement and optimize model-serving pipelines.

• Optimize, evaluate, and fine-tune deep learning models within the realms of LLM, multimodal, and Generative AI.

• Scale deep learning model performance across various architectures and types of NVIDIA accelerators.

• Contribute features and code to NVIDIA's inference libraries, vLLM, SGLang, FlashInfer, and LLM software solutions.

• Collaborate with teams across frameworks and NVIDIA libraries to develop inference optimization solutions.

⛳️ Requirements

• Master's or PhD, or equivalent experience in a pertinent field such as Computer Engineering, Computer Science, EECS, or AI.

• A minimum of 5 years of relevant software development experience.

• Exceptional C/C++ programming and software design capabilities.

• SW Agile skills are advantageous.

• Experience with Python is a plus.

• Prior experience with training, deploying, or optimizing deep learning model inference in production is beneficial.

• A background in performance modeling, profiling, debugging, code optimization, or knowledge of CPU/GPU architectures is a plus.

• Experience contributing to deep learning software projects like PyTorch, vLLM, and SGLang is a distinct advantage.

• Familiarity with multi-GPU communications, including NCCL and NVSHMEM, is a differentiator.

• Experience in building and delivering products to enterprise clients is a differentiator.

• GPU programming experience with CUDA, OAI Triton, or CUTLASS is a differentiator.

🏝️ Benefits

• Highly competitive salaries.

• Extensive benefits package.

• A work environment that fosters diversity, inclusion, and flexibility.