ML OPS Engineer

Key Responsibilities

• Develop, deploy, and maintain ML services using

  Langserve

  for efficient model serving.
• Monitor model performance and manage observability using

  Langfuse

  .
• Containerize applications and services using

  Docker

  for consistent development and production environments.
• Orchestrate and manage containerized workloads using

  Kubernetes

  (EKS/GKE/AKS or self-managed).
• Write and maintain

  Groovy scripts

  for automation and CI/CD pipelines.
• Collaborate with data scientists, backend engineers, and DevOps teams to ensure smooth ML model delivery.
  
• Optimize infrastructure cost, reliability, and scalability for ML workflows.
  
• Implement monitoring, alerting, and logging best practices.
  

Required Skills

• Proven experience in

  ML Ops

  and deploying machine learning models in production.
• Hands-on knowledge of

  Langserve

  for LLM or ML model inference.
• Experience using

  Langfuse

  for logging, tracing, and monitoring LLM applications.
• Strong understanding of

  Docker

  and containerization best practices.
• Expertise with

  Kubernetes

  and managing cloud-native environments.
• Solid scripting skills in

  Groovy

  , especially in Jenkins or CI/CD automation.
• Familiarity with CI/CD tools (e.g., Jenkins, GitHub Actions, GitLab CI).
  
• Working knowledge of cloud services (AWS, GCP, or Azure).
  

Preferred Qualifications

• Experience with LLMOps or working on LLM-based pipelines.
  
• Familiarity with observability stacks (Prometheus, Grafana, ELK).
  
• Exposure to infrastructure-as-code (Terraform, Helm, etc.).