AI Engineer Agentic AI & GraphRAG

AI Engineer – Agentic AI & GraphRAG Development

We are looking for a talented and self-driven AI Engineer to
work on our GraphRAG (Graph Retrieval-Augmented Generation) systems and
contribute to the evolution of Graph's MCP (Model Context Protocol) tooling
framework. This role spans AI/LLM integration, graph query pipelines, and
developer tooling — helping build a platform that blends graph intelligence
with generative AI.

This is a role for someone who enjoys solving open-ended
problems. You'll work from clear objectives rather than fully scoped tickets,
contribute to the direction of GraphRAG and agentic-AI components, and write
the code to bring them to life alongside a broader engineering team.

Responsibilities

• Contribute
  to GraphRAG systems and MCP framework components, working through
  ambiguous technical problems with guidance from senior engineers where
  needed
  
• Design
  and build MCP tools and components, including orchestration logic,
  agentic-AI workflows, LLM interface layers, and graph-native operators
  
• Build
  integration code between TigerGraph's GSQL, vector indexing systems, and
  external LLMs (e.g., OpenAI, Gemini, LLaMA)
  
• Develop
  reusable modules, prompts, and components for cognitive agents (e.g.,
  GraphRAG agents, schema routers, grounded QA evaluators) with attention to
  developer experience
  
• Collaborate
  with TigerGraph's platform, AI research, and product teams to help shape
  the MCP engineering roadmap
  
• Write
  test suites and benchmark GraphRAG system performance for hallucination,
  groundedness, latency, and answer usefulness
  
• Contribute
  to internal documentation and SDKs to support MCP developer usability
  

Required:

• Experience: 3-6 years of hands-on software engineering experience, including exposure
  to LLM orchestration, agent systems, or AI SDKs
  
• Ownership
  Mindset: Comfortable working through loosely defined problems and
  proposing solutions, with support from senior team members as needed
  
• Strong
  programming skills in Python
  
• Working
  experience with TigerGraph (GSQL queries, RESTPP, schema modeling), or
  strong experience with another graph database and willingness to ramp up
  
• Familiarity
  with Graph-based retrieval-augmented generation (GraphRAG) architectures
  and their application in real-world AI systems
  
• Experience
  using frameworks like LangChain, LangGraph, or similar agent-based LLM
  tools and prompt templating
  
• Understanding
  of vector indexing and similarity search; familiarity with vector stores
  (e.g., FAISS, Milvus)
  
• Ability
  to build usable internal tools for developers or data scientists
  

Preferred:

• Prior
  experience contributing to tools, platforms, or APIs used by other AI
  engineers or ML practitioners
  
• Background
  in knowledge graphs, graph neural networks, or knowledge-based QA systems
  
• Familiarity
  with Docker/Kubernetes, FastAPI, and distributed compute systems
  
• Contributions
  to open-source projects in the graph, ML, or LLM domains
  

Requirements

Required:

●       High Agency & Self-Drive: A proven track record of taking vague
technical concepts, figuring out the optimal engineering path, and writing
production-ready code without requiring heavy hand-holding or day-to-day
micro-direction.

●       Product-Minded Engineer: You don't just write scripts; you think deeply about the
"why" behind the feature and care immensely about how other
developers will interact with your code.

●       Strong programming skills in
Python; deep hands-on experience building LLM orchestration tools, agent
systems, or AI SDKs.

●       Hands-on
experience with TigerGraph (GSQL queries, RESTPP, schema modeling).

●       Familiarity
with Graph-based retrieval-augmented generation (GraphRAG) architectures and
their application in real-world AI systems.

●       Experience
using or actively contributing to frameworks like LangChain, LangGraph, or
similar agent-based LLM tools and prompt templating.

●       Understanding
of vector indexing and similarity search; familiar with modern vector stores
(e.g., FAISS, Milvus).

●       Ability to design exceptionally
usable internal tools for developers or data scientists.

Preferred:

●       Prior experience developing tools,
platforms, or APIs used by other AI engineers or ML practitioners.

●       Background in knowledge graphs,
graph neural networks, or knowledge-based QA systems.

●       Familiarity
with Docker/Kubernetes, FastAPI, and distributed compute systems.

●       Contributions to open-source
projects in the graph, ML, or LLM domains.