Senior System Software Engineer - Local AI Automation

NVIDIA NVIDIA · Semiconductors · Pune, India

Senior System Software Engineer focused on building and maintaining infrastructure for deploying AI applications and models on local devices, including managing inference backends, automating model downloads, analyzing data, and implementing CI/CD pipelines.

What you'd actually do

  1. Design, implement, and maintain robust infrastructure to efficiently run various AI workloads through different inference backends like Llama.cpp, Ollama, Pytorch, WinML, TRT-RTX, and others.
  2. Scope out the requirements for deploying various AI applications, benchmarks and models in automation, and develop solutions to measure accuracy, functionality and performance.
  3. Develop Infrastructure to download AI models from various sources and efficiently manage a local repository, create an automated synchronization mechanism to keep repository up to date.
  4. Analyze large datasets to derive insights and design visualizations, implement data processing engines to transform raw data into a more usable format for developers to review.
  5. Collaborate with internal Local AI developers to identify and implement features in automation that help them quickly debug/isolate issues.

Skills

Required

  • 5+ years of experience with B.Tech or higher degree in Computer Science, Information Technology, Software engineering, or related field.
  • Strong analytical and problem-solving abilities
  • application development using C#, Java, or another programming language
  • scripting language such as Python, Perl, or PHP
  • Familiarity with databases and SQL
  • experience working with source control systems
  • CI/CD pipelines
  • Git
  • Perforce
  • Jenkins
  • Outstanding written and oral communication skills

Nice to have

  • Experience of building robust backend automation systems with hands on experience of working the databases.
  • Familiarized in setting up visualization interfaces using Grafana, Kibana, or similar platforms.
  • Hands on background with managing git CICD pipelines, Kubernetes and Docker.
  • Hands on experience with inference frameworks Llama.cpp, Ollama, Pyotrch etc.

What the JD emphasized

  • robust infrastructure
  • AI applications
  • AI models
  • automation
  • inference backends
  • deploying various AI applications
  • automated synchronization mechanism
  • data processing engines
  • debug/isolate issues
  • CI/CD pipelines
  • inference frameworks

Other signals

  • Develop and maintain infrastructure for deploying AI applications and models
  • Design and implement CI/CD pipelines for automated build and deployment
  • Analyze large datasets to derive insights and design visualizations