Senior Software Engineer, NIM Production

at Nvidia
πŸ“ United States
USD 184,000-356,500 per year
SENIOR
βœ… Remote

SCRAPED

Used Tools & Technologies

Not specified

Required Skills & Competences ?

Docker @ 4 Kubernetes @ 4 CI/CD @ 4 Leadership @ 7 Helm @ 4 Microservices @ 4 Debugging @ 4 API @ 4 LLM @ 4

Details

NVIDIA is the platform upon which every new AI-powered application is built. This role involves developing components used by the software factory automation for NVIDIA Inference Microservices (NIMs) and its deployed services. The candidate will drive innovation in high-performance inferencing for AI models, developing scalable, high-availability services leveraging thousands of GPUs.

Responsibilities

  • Design, build, and optimize containerized inference execution for LLM applications, ensuring efficiency and scalability.
  • Ensure performance and scalability of NIMs through performance measurement and optimization.
  • Develop and optimize core components of NIMs using container technologies.
  • Collaborate with software engineers, researchers, SREs, and product managers to improve inference solutions and APIs.
  • Mentor and grow team members to foster technical development.

Requirements

  • Advanced programming skills in building distributed compute systems, backend services, microservices, and cloud technologies.
  • Experience productionizing and deploying LLM models.
  • Experience working with cross-functional teams including principals and architects.
  • Proven mentorship abilities.
  • Deep expertise in distributed containerized applications using Docker, Kubernetes, Helm Charts.
  • Passion for building scalable and performant microservices.
  • Strong interpersonal and leadership skills.
  • Proven experience debugging and performance tuning distributed microservices or cloud systems.
  • Degree in Computer Science, Computer Engineering, or related field (BS or MS) or equivalent experience.
  • 6+ years of relevant experience.

Ways to Stand Out

  • Experience with open-source inference engines and serving stacks.
  • Benchmarking generative AI model performance.
  • Experience building/deploying containers and CI/CD pipelines for microservices.
  • Prior work in large-scale backend development.

Compensation

The base salary range is 184,000 USD - 356,500 USD, determined by location, experience, and peer pay. Additional equity and benefits are available.

Additional Information

NVIDIA values diversity and is an equal opportunity employer.