Agentic AI Architecture & Development

Agentic AI Architecture & Development

Location: Bangalore (Hybrid – 3 days WFO mandatory)

About the Role

We are seeking an experienced Agentic AI Architect & Developer to design and build production-grade multi-agent systems leveraging LangGraph, LangChain, CrewAI, and AutoGen. The ideal candidate will have strong expertise in Agentic AI, LLM integration, and advanced Python development with proven experience in enterprise-scale AI/ML environments.

Key Responsibilities

• Architect and implement multi-agent orchestration patterns (planning, tool use, persistent state, memory, reflection).
  

• Develop and optimize RAG pipelines with embeddings, chunking, and vector database integration.
  

• Integrate and manage LLM/SLM services (OpenAI, Azure OpenAI, Anthropic, open-source models) with cost optimization.
  

• Build scalable backend services using Python (FastAPI), distributed task processing (Celery), and event-driven microservices.
  

• Implement caching, rate limiting, persistent agent state, and conversation memory strategies.
  

• Lead innovation initiatives, mentor engineers, and champion adoption of AI-powered development tools (Cursor AI, GitHub Copilot).
  

Required Qualifications

• 6+ years of proven software engineering experience with significant hands-on AI/ML work in enterprise environments.
  

• Strong proficiency in Python with production AI applications.
  

• Hands-on experience with LangGraph or similar frameworks (LangChain, CrewAI, AutoGen).
  

• Expertise in LLM API integration and prompt engineering.
  

• Experience designing and implementing RAG systems with vector databases.
  

• Solid understanding of multi-agent system design and orchestration.
  

• Strong communication skills to explain complex AI concepts to diverse stakeholders.
  

Preferred Qualifications

• Experience with vector databases (Qdrant, Pinecone, Weaviate, ChromaDB).
  

• Familiarity with Databricks Genie or AWS Bedrock AgentCore.
  

• Knowledge of model fine-tuning, quantization, and serving optimization.
  

• Experience with containerization (Docker, Kubernetes) and event-driven autoscaling (KEDA).
  

• Understanding of AI safety, responsible AI principles, and enterprise governance.
  

Interview Process

• 2 rounds of interviews.
  

• General shift timing; no weekend/on-call support required.
  

• Candidates with ≤15 days notice period or serving notice preferred.