We are looking for an experienced AI Agent Engineer with strong expertise in building and deploying agentic and LLM-powered systems. The ideal candidate will have hands-on experience across AI orchestration frameworks, retrieval systems, and scalable backend architectures.
Roles and Responsibilities
- Design, develop, and deploy agentic AI systems using modern frameworks and orchestration patterns.
- Build and optimize LLM-based applications, including multi-agent workflows and tool-augmented reasoning systems.
- Develop and maintain Retrieval-Augmented Generation (RAG) pipelines for enterprise-scale applications.
- Architect scalable backend services and APIs to support AI-driven products.
- Collaborate with cross-functional teams to integrate AI capabilities into production systems.
Required Skills & Experience
AI / LLM / Agentic Systems
- Strong hands-on experience with agentic AI frameworks such as MCP, ADK, LangGraph, and LangChain
- Deep expertise in LLM integration, orchestration, and prompt/agent design
- Experience building multi-agent systems and complex AI workflows
- Strong understanding of RAG architectures
Search, Data & Knowledge Systems
- Experience with vector databases (Pinecone, FAISS, Weaviate, etc.)
- Experience with graph databases (Neo4j, Amazon Neptune, etc.)
- Strong knowledge of semantic search, embeddings, and knowledge graphs
Cloud & Infrastructure
- Strong experience with cloud platforms, preferably GCP (Vertex AI, Cloud Run, GKE)
- Exposure to Azure or other cloud environments is a plus
- Understanding of scalable AI deployment patterns
Backend & System Design
- Strong background in API design and development
- Experience with microservices architecture and distributed systems
- Proficiency in Python for backend development