About the job
We are looking for an engineer who wants to take the world's largest and most capable AI models and optimize them for use in a high-volume, low-latency, and high-availability production and research environment.
Responsibilities
Work alongside machine learning researchers, engineers, and product managers to bring our latest technologies into production.
Work alongside researchers to enable advanced research through awesome engineering.
Introduce new techniques, tools, and architecture that improve the performance, latency, throughput, and efficiency of our model inference stack.
Build tools to give us visibility into our bottlenecks and sources of instability and then design and implement solutions to address the highest priority issues.
Optimize our code and fleet of Azure VMs to utilize every FLOP and every GB of GPU RAM of our hardware.
Qualifications
Minimum
Have at least 5 years of professional software engineering experience.
Preferred
Have an understanding of modern ML architectures and an intuition for how to optimize their performance, particularly for inference.
Own problems end-to-end, and are willing to pick up whatever knowledge you're missing to get the job done.
Have or can quickly gain familiarity with PyTorch, NVidia GPUs and the software stacks that optimize them (e.g. NCCL, CUDA), as well as HPC technologies such as InfiniBand, MPI, NVLink, etc.
Have experience architecting, building, observing, and debugging production distributed systems. Bonus point if worked on performance-critical distributed systems.
Have needed to rebuild or substantially refactor production systems several times over due to rapidly increasing scale.
Are self-directed and enjoy figuring out the most important problem to work on.
Have a humble attitude, an eagerness to help your colleagues, and a desire to do whatever it takes to make the team succeed.