Senior Deep Learning Engineer

Job Summary

Leading architecture and performance initiatives, the full-time Senior Deep Learning Algorithm Engineer will advance the Dynamo open-source distributed inference platform for large-scale AI services, collaborating with research, software, systems, and hardware teams in a hybrid work environment.

Key responsibilities

• Design, build, and maintain integrations for open-source frameworks such as vLLM, SGLang, and TRTLLM
• Collaborate with open-source communities to improve latency, throughput, reliability, and efficiency
• Identify and eliminate bottlenecks across various components including runtimes, kernels, and networking

Required qualifications

• BS, MS, or PhD in Computer Science, Electrical Engineering, Computer Engineering, or a related field (or equivalent experience)
• 3+ years of experience in building, profiling, and debugging performance-critical distributed or ML systems
• Strong programming skills in Python and/or Rust, C++
• Understanding of modern ML architectures and inference techniques