Remote - AI/ML Platform Engineer

What You'll Build

Multi-agent LLM orchestration using LangGraph / LangChain for autonomous incident response

RAG pipelines over runbooks, topology graphs, and observability telemetry (Pinecone / pgvector)

Knowledge graph-based topology reasoning using Neo4j

Integration with OpenTelemetry, Prometheus, Grafana, and Datadog

Auto-PR generation for Terraform, Helm, and Kubernetes manifests

Bidirectional ServiceNow / Jira integration via MCP server

Required Skills

LangGraph or LangChain (multi-agent orchestration — not just chatbots)

Kubernetes, Helm, ArgoCD, or Terraform

Python (FastAPI preferred), async, production-grade code

OpenTelemetry or similar observability stack

RAG pipeline design (chunking, retrieval, reranking)

3+ years of relevant experience; IIT/IIIT/NIT background preferred

Bonus Skills

Neo4j or graph databases

TimescaleDB or InfluxDB (time-series anomaly detection)