MLOps Engineer
Core
Lead the deployment, monitoring, orchestration, and operational reliability of production LLM applications and agentic AI platforms.
Role type
Senior MLOps / LLMOps Engineer
Builds
Multi-step agentic workflows, data pipelines, and retrieval-augmented systems
Domain
AI Infrastructure / Cloud Engineering
Deliverable
production ML models
Required skills
Kubernetes (EKS, GKE, AKS), Python, CI/CD pipelines, Infrastructure as Code (Terraform, Pulumi), LLM-specific tracing and evaluation, agentic architectures, prompt chaining, function calling, non-deterministic application behavior
Preferred skills
RAG pipelines, vector databases, agent orchestration frameworks (LangChain, LangGraph, LlamaIndex, AutoGen, CrewAI), high-performance LLM serving engines (vLLM, TGI, Ollama, TensorRT-LLM), AI security practices
Technologies
Kubernetes, Prometheus, Grafana, Datadog, OpenTelemetry, LangSmith, Phoenix/Arize, Langfuse, TruLens, GitHub Actions, GitLab CI, ArgoCD, Terraform, Pulumi, vLLM, TGI, Ollama, TensorRT-LLM, Pinecone, Qdrant, Milvus, pgvector, Weaviate, LangChain, LangGraph, LlamaIndex, AutoGen, CrewAI
Responsibilities
Design, deploy, and manage LLM services and agentic applications inside high-throughput Kubernetes clusters; Automate containerized deployments and rollout strategies for LLM/Agent releases; Support and maintain production operation of agentic AI workflows; Rapidly triage and resolve issues across AI application logic and cloud infrastructure; Build end-to-end monitoring and evaluation frameworks for AI output accuracy and metrics; Implement trace-level observability for agent execution paths; Monitor and optimize data pipelines powering AI workloads; Manage resource allocation and cloud infrastructure expenditure to optimize performance
Seniority
Senior, hands-on IC
