India Template

Cognite Cognite · Industrial · India · Engineering

Software Engineer to join the Context Services team, focusing on transitioning AI/ML models and LLM agents from experimentation to scalable production. Responsibilities include developing low-latency APIs, building automated pipelines for deployment and monitoring, and ensuring system health for industrial AI solutions.

What you'd actually do

  1. Package AI/ML models and LLM workflows, developing low-latency APIs to support thousands of concurrent users.
  2. Partner with our AI and product teams to translate complex industrial data challenges and agentic workflows into reliable software services.
  3. Build and maintain automated pipelines for data processing, model deployment, agent monitoring, and system evaluation.
  4. Implement monitoring solutions to track system performance, inference costs, and latency bottlenecks in production.
  5. Stay up-to-date with emerging engineering trends in ML and Generative AI, participating in research and prototyping to improve our internal systems.

Skills

Required

  • Python
  • FastAPI
  • asynchronous tasks
  • containers
  • CI/CD pipelines

Nice to have

  • MLOps
  • Generative AI
  • LLM lifecycle

What the JD emphasized

  • low-latency APIs
  • agentic workflows
  • automated pipelines
  • monitoring solutions
  • inference costs

Other signals

  • transition predictive models and LLM agents from the experimentation phase into scalable production environments
  • writing clean, efficient code to serve these AI solutions to our users quickly and reliably
  • low-latency APIs to support thousands of concurrent users
  • agentic workflows into reliable software services
  • automated pipelines for data processing, model deployment, agent monitoring, and system evaluation
  • monitoring solutions to track system performance, inference costs, and latency bottlenecks