Description

Lead the design and delivery of enterprise-scale agentic AI systems across multi-cloud environments.

This role is on-site.

Responsibilities

• Own the Agentic AI Platform architecture, including orchestration, RAG pipelines, guardrails, and evaluation frameworks.
• Define and enforce multi-cloud standards (AWS, Azure, GCP) covering VPC, IAM, networking, and security policies.
• Design complex multi-agent workflows, state machines, and orchestration patterns with reliable rollout strategies.
• Establish API and SDK standards (Python/TypeScript) and ensure OpenTelemetry-based observability across services.
• Lead incident response, define SLIs/SLOs, and drive governance processes including ADRs and architecture reviews.

Required Skills

• 9+ years of experience in software architecture and engineering.
• Deep expertise in Agentic AI systems, LLMs, and orchestration frameworks.
• Strong knowledge of RAG pipelines, vector databases (Pinecone, Weaviate, pgvector), and retrieval strategies.
• Hands-on experience with multi-cloud environments (AWS, Azure, GCP).
• Proficiency in Python, microservices, and API development.
• Expertise in observability tools (OpenTelemetry, Grafana, Prometheus).
• Strong understanding of security practices (IAM, encryption, mTLS, secrets management).
• Experience with Kubernetes and CI/CD pipelines.

Preferred Skills

• Experience with LangGraph, AutoGen, CrewAI, or LlamaIndex.
• Familiarity with advanced RAG techniques (hybrid search, reranking, caching).

Key Skills

Education

Any Graduate