LLMOps Engineer
Family: Data & AI
Runs the operational side of LLM applications, handling deployment, evaluation, monitoring, and cost of models in production.
Day to day
Builds pipelines to deploy and version prompts and models, sets up eval and monitoring, manages inference cost and latency, and automates rollout.
Core skills
- LLM serving
- evaluation
- observability
- prompt versioning
- cost/latency tuning
- pipelines