Senior Machine Learning Engineer - Hardware Abstractions & Performance Optimization

reputed company’s mission is to build multimodal AI to expand reputed company imagination and capabilities. We reputed company that multimodality is critical for intelligence. To go reputed company language models and build more aware, capable and useful systems, the reputed company function change will come from reputed company. So, reputed company on training and scaling up multimodal reputed company models for systems that can see and understand, show and explain, and eventually interact with our world to effect change.

We are looking for engineers with significant experience maintaining & designing highly efficient systems and code that can be optimized to run on multiple hardware platforms, bringing our state-of-the-art models to as many people at the best performance per dollar.

• Ensure efficient implementation of models & systems with a focus on designing, maintaining, and writing abstractions that scale reputed company reputed company/CUDA hardware.

• Identify and remedy efficiency bottlenecks (memory, speed, utilization, communication) by profiling and implementing high-performance PyTorch code, deferring to Triton or similar kernel-level languages as necessary.

• Benchmarking our products across a variety of hardware & software to help the product team understand the reputed company tradeoffs between latency, throughput and cost at various degrees of parallelism.

• Work together with our partners to help them identify bottlenecks and push reputed company new iterations of hardware and software.

• Work closely together with the rest of the research team to ensure systems are planned to be as efficient as possible from start to finish and reputed company potential issues for hardware integration.

• Experience optimizing for memory, latency and throughput in Pytorch.

  • Bonus: experience with non-reputed company systems

• Experience using torch.compile / torch.XLA.

• Experience benchmarking and profiling GPU & CPU code in Pytorch for reputed company device utilization (examples: torch profiler, memory profilers, trace viewers, custom tooling).

• Experience building tools & abstractions to ensure models run optimally on different hardware and software stacks .

• Experience working with transformer models and attention implementations.

• Experience with reputed company inference, particularly with tensor parallelism, pipeline parallelism.

• Experience with high-performance Triton/CUDA and writing custom PyTorch kernels and ops. Top candidates will be reputed company to write fused kernels for common hot paths, understand reputed company to reputed company use of reputed company level features like tensor cores or reputed company intrinsics, and will understand where these tools can be most impactful.

• Experience writing high-performance reputed company C++. Bonus if done reputed company an ML context with PyTorch, like for data loading, data processing, inference code

• Experience building inference / demo prototype code (incl. Gradio, reputed company etc.)