Senior AIOps Engineer

AI/LLM Ops Specialist

(Agentic AI & AI Native Infrastructure)

We are seeking an experienced AI/LLM Ops Specialist to own the deployment and operations of agentic AI systems at enterprise scale. You will accelerate our shift from AI enabled workflows to AI native infrastructure, implementing and running autonomous multi agent LLM solutions that drive mission critical processes.

• Architect & Deploy Agentic AI Systems: Design, implement, and maintain multi agent orchestration frameworks (e.g., FastAgent, FastMCP, LangGraph, AutoGen, CrewAI) to coordinate autonomous LLM workflows.


• LLMOps & RAG Integration: Develop and operationalize RAG workflows, vector stores, and knowledge graph connectors.


• Monitoring, Observability & Reliability: Implement end to end observability using Prometheus/Grafana, OpenTelemetry, and incident playbooks.


• Governance, Security & Compliance: Enforce data governance, PII handling, and prompt audit trails across agent interactions.


• Collaboration & Enablement: Partner with data engineers, MLOps, and DevOps to align CI/CD for AI workloads and mentor teams.


• Continuous Improvement: Benchmark agent performance, optimize token usage, and research emerging agentic AI frameworks.

1. 5+ years in production ML/LLM operations, with 2+ years in autonomous agent systems.


2. Hands on experience with FastAgent, FastMCP, LangGraph, AutoGen, CrewAI, or similar.


3. Expertise in Kubernetes, Docker, Terraform (or Pulumi), and GitOps workflows.


4. Proven track record implementing RAG pipelines with Pinecone, Elasticsearch, or similar.


5. Proficient in observability tools (Prometheus, Grafana, Jaeger/OpenTelemetry).

• Open source contributions or conference talks on agentic AI or LLMOps.


• Experience optimizing inference with vLLM, TensorRT LLM, or similar libraries.


• Certifications in cloud architecture or AI security.


• Familiarity with multi modal agent workflows or edge deployed agents. Experience leading AI first governance and decision loop monitoring.

• Agentic AI Frameworks: FastMCP, FastAgent, Agent Builder, LangGraph, AutoGen, CrewAI


• Protocols & Standards: Model Context Protocol (MCP), A2A


• LLM Providers: OpenAI, Anthropic, Google Gemini


• Vector Stores & Indexing: Pinecone, Redis Vector DB, Weaviate, PGVector, LlamaIndex


• Monitoring & Observability: LangSmith, LangFuse, Arize, Coralogix


• Cloud & Orchestration: Kubernetes, Docker, AWS Bedrock/SageMaker, GCP Vertex AI, Azure ML


• Inference Optimization: vLLM, TensorRT LLM, Ollama


• IaC & CI/CD Tools: Terraform, Helm, GitHub Actions

Join us and be the driving force behind our evolution into an AI native, agentic future, crafting the autonomous systems that will power tomorrow s innovation.