NVIDIA is seeking a Software Engineering Manager to lead the development for the Dynamo engineering team, NVIDIA’s high-performance, low-latency inference platform for serving generative AI and reasoning workloads at scale. The team accelerates deployment of cutting-edge models across diverse engines and architectures, enabling breakthroughs from real-time LLM serving to complex multi-GPU, multi-node pipelines.
Requirements
- 10+ years of overall experience in developing large distributed systems.
- 2+ years of experience managing of AI and SW development teams.
- Experience in developing and maintaining LLM or GenAI infrastructure
- Hands-on experience developing large-scale distributed systems
- Strong technical background in cloud/distributed systems.
- Good knowledge of CPU and/or GPU hardware architecture
- Experience with LLM frameworks like vLLM & TRT-LLM.
Responsibilities
- Mentor, grow, and develop the Dynamo engineering team and be responsible for planning and execution of projects and workflows.
- Work across several teams and orgs to build platforms that use the latest developments in LLM inferencing.
- In this role, you will be collaborating with research and development teams and serve a large user base (software teams both internal and external to NVIDIA).
- Align priorities across collaborators and define metrics for measuring the success of the product/team.
- Stay updated with the latest trends in AI, ML, and infrastructure, proactively seeking opportunities to integrate advancements into NVIDIA's LLM and AI infrastructure solutions.
Other
- Masters or PhD or equivalent experience in Computer Science, computer architecture, or related field.
- Excellent communication, collaboration and problem-solving skills, with a dedication to encouraging an inclusive and diverse workplace.
- Experience working in a globally distributed organization.
- Are you creative and autonomous?
- Do you love a challenge?
