Senior DevTech Compute Engineer, Compression and Data Processing

About the role

NVIDIA is currently seeking a highly motivated Senior DevTech Compute Engineer for Compression and Data Processing! Would you enjoy prototyping and developing ground breaking methods and data formats to accelerate complex distributed workflows? Do you love investigating and overcoming system-level bottlenecks for multi-stage and multi-IP overlapped workloads? Do you prefer squeezing all useful entropy out of data, whether it is columnar row-groups, DL tensors or multidimensional images and videos? Are you excited about co-designing the systems, software components and hardware blocks to define the next frontier for distributed data processing? If so, this is an outstanding opportunity for you to join the Developer Technology Compute team.

Data analytics, databases and distributed data processing is one of the fastest growing domains for non-CPU accelerated computing: “on-the-wire” compression and decompression is already part of the switches and DPUs, low-latency queries across huge amounts of data in data lakes at scale in the middle of the RL training run defines the business agility. Here at NVIDIA Devtech Compute team we take a holistic approach to data movement, late materialization, memory management and spilling, parallel algorithms, collectives and compression and quantization. Read more from the team: Designing GPU Query Engines, Cut Checkpoints Costs or take a look at some of the projects in depth: NVIDIA nvCOMP, NVIDIA GPU Query Engine (GQE), NVIDIA cuCollections.

What you will be doing:

- In this role, you will prototype and integrate novel approaches to GPU-accelerated distributed data processing domains: dataframe analytics, high-throughput low-latency advanced lossless and lossy compression methods, transactional and vector databases.

- Work directly with other technical experts in their fields (industry and academia) to perform in-depth analysis and optimization of complex data intensive workloads to ensure the best possible performance of current heterogeneous GPU/CPU architectures.

- Influence the design of next-generation hardware architectures, software, and programming models in collaboration with research, hardware, system software, libraries, and tools teams at NVIDIA.

- Work directly with the NVIDIA largest customers and CSPs to integrate the solutions at Speed-Of-Light, and influence open standards in data analytics and compression

What we need to see:

- Masters or PhD in Computer Science, Computer Engineering, Applied Math and/or related computationally focused science degree (or equivalent experience).

- At least 5+ years of relevant work or research experience, with a track record in the state-of-the-art systems or complex projects, involving cross-team collaboration and solid prioritization skills.

- Hands-on experience with low-level parallel programming across execution units (CPU/GPU/NPU/ASICs), e.g., CUDA, ROCm, Metal, OpenACC, OpenMP, MPI, pthreads, TBB, etc.

- Fluency in C/C++, algorithms and data structures