Agentic AI Engineer

We are looking for an experienced Senior Agentic AI Engineer / AI Solutions Architect with 5+ years of software engineering experience and strong expertise in Backend Development, Generative AI and Agentic AI. The ideal candidate should have hands-on experience designing, developing and deploying production-ready AI agents and multi-agent systems. They should be strong in Python, RAG, LangGraph, CrewAI, MCP, distributed systems and cloud technologies. The candidate should be capable of owning end-to-end AI solutions, from architecture and development to production deployment, monitoring and client delivery.

Responsibilities:

• Design, develop and deploy end-to-end Agentic AI solutions.
• Build multi-agent workflows using LangGraph, CrewAI or equivalent frameworks.
• Develop RAG pipelines and integrate LLMs with enterprise applications.
• Implement MCP, tool calling, agent memory and context engineering.
• Develop scalable backend services, APIs and microservices.
• Work with Kafka, RabbitMQ and event-driven architectures.
• Implement AI evaluation, monitoring, observability and guardrails.
• Deploy and manage AI applications on AWS, Azure or GCP.
• Handle production debugging, performance optimisation and incident resolution.
• Lead client discussions, requirement gathering and solution architecture.
• Mentor engineering teams and establish AI engineering best practices.

Requirements:

• 5+ years of overall software engineering experience.
• Strong backend development background.
• Hands-on experience with production-grade Agentic AI applications.
• Experience building multi-agent systems using LangGraph or CrewAI.
• Strong understanding of RAG, MCP and LLM integrations.
• Experience deploying and maintaining AI solutions in cloud environments.
• Ability to independently lead client discussions and technical architecture.

Must-have skills:

• 5+ years in software engineering
• Programming
• Strong Python
• Agentic AI
• Hands-on experience building AI agents
• Frameworks
• LangGraph / CrewAI / equivalent
• RAG
• Hands-on RAG implementation
• MCP
• Model Context Protocol implementation
• LLM
• Tool calling, context engineering and agent memory
• Backend
• FastAPI, REST APIs, microservices
• Architecture
• Distributed systems and system design
• Messaging
• Kafka / RabbitMQ
• Cloud
• AWS / Azure / GCP
• Production
• AI deployment, monitoring and debugging

Good-to-have Skills:

• LangSmith / Langfuse
• Vector databases - Pinecone, FAISS, Milvus, Weaviate, Chroma
• Docker and Kubernetes
• CI/CD and release engineering
• OpenTelemetry and observability
• AI security, governance and guardrails
• Human-in-the-loop workflows
• Client-facing consulting and solution architecture

Skills

AI Agents, Agentic AI, CrewAI, FastAPI, Kafka, LangGraph, Multi-Agent, Python, RAG