Agentic AI Developer

We are seeking a highly skilled Agentic AI / Semantic Solutions Architect to design and prototype advanced agent-layer architectures that operate on enterprise semantic data platforms. This role sits at the intersection of LLM orchestration, knowledge graphs, and semantic data modeling, focusing on building POC-level intelligent agent solutions rather than production-scale systems.

The ideal candidate will have deep expertise in agent-based AI systems, GraphRAG architectures, and context engineering, with the ability to design frameworks where autonomous agents can effectively interpret and reason over structured knowledge.

Key Responsibilities

· Architect and design agentic AI workflows that consume outputs from semantic layers, including knowledge graphs, ontologies, and metadata catalogs
· Develop and prototype GraphRAG pipelines that combine graph traversal with vector-based retrieval for accurate, domain-grounded responses
· Define and implement context engineering strategies, including metadata injection, chunking, and semantic optimization for LLM prompts
· Design and build Model Context Protocol (MCP) server patterns to enable seamless interaction between agents and semantic data systems
· Develop LLM orchestration workflows using frameworks such as LangChain, LangGraph, LlamaIndex, or AutoGen
· Build pipelines for automated metadata extraction and semantic tagging using NLP and LLM-based approaches
· Collaborate with Semantic Data Architects to ensure ontologies and graph structures are optimized for agent traversal and querying
· Prototype agent-based solutions for business use cases such as:
· Credit risk analysis
· Customer data onboarding workflows

 
Mandatory Skills

· Strong expertise in Agentic AI architecture (multi-agent systems, tool usage, planning loops)
· Hands-on experience with GraphRAG design (hybrid graph + vector retrieval systems)
· Experience in LLM orchestration frameworks:
· LangChain, LangGraph, LlamaIndex, or AutoGen
· Deep understanding of context engineering techniques (chunking, windowing, semantic compression)
· Experience designing and integrating Model Context Protocol (MCP)
· Strong knowledge of semantic systems such as:
· Knowledge graphs
· Ontologies
· Metadata-driven architectures


Nice to Have Skills

· Experience with Google Vertex AI (Agent Builder / Search)
· Knowledge of Google Cloud Platform Spanner Graph
· Familiarity with metadata platforms like Collibra or Google Dataplex
· Experience with vector databases:
· Pinecone, Weaviate, pgvector, Vertex AI Vector Search
· Prior experience in regulated domains such as financial services or legal systems