About the job
As a Distributed LLM Inference Engineer, you will help systems and optimizations that push the boundaries of performance for inference at large scale. This is an incredibly critical role to Anyscale as it allows us to achieve a market leading position for AI infrastructure.
Responsibilities
- Iterate very quickly with product teams to ship the end to end solutions for Batch and Online inference at high scale which will be used by open-source Ray users and customers of Anyscale
- Work across the stack integrating Ray Data and LLM engine providing optimizations achieving low cost solutions for large scale ML inference
- Integrate with Open source software like vLLM, work closely with the community to adopt these techniques in Anyscale solutions, and also contribute improvements to open source
- Follow the latest state-of-the-art in the open source and the research community, implementing and extending best practices
Qualifications
Minimum
- Familiarity with running ML inference at large scale with high throughput and low latency
- Familiarity with deep learning and deep learning frameworks (e.g. PyTorch)
- Solid understanding of distributed systems, ML inference challenges
Preferred
- ML Systems knowledge
- Experience using Ray
- Work closely with community on LLM engines like vLLM, TensorRT-LLM
- Contributions to deep learning frameworks (PyTorch, TensorFlow)
- Contributions to deep learning compilers (Triton, TVM, MLIR)
- Prior experience working on GPUs / CUDA