AI/ Full Stack Developer

Full JD

Deep domain expertise
AI & Data capabilities
Engineering & Operations excellence
Job Title: AI / Full Stack Engineer (GCP, LLM, Graph RAG)




Location: Dallas, TX / Tampa, FL
Duration: Contract Onsite




Role Overview




We are seeking an experienced AI / Full Stack Engineer to work on cutting-edge AI-driven applications leveraging Large Language Models (LLMs), graph databases, and cloud-native services. The ideal candidate will have strong expertise across both backend and frontend development, along with hands-on experience building intelligent applications using GCP and modern AI frameworks.




Key Responsibilities




Design, develop, and deploy full stack applications using React, Node.js, and Python
Build and integrate LLM-powered solutions using APIs such as Vertex AI, Gemini, OpenAI, or Anthropic
Implement RAG (Retrieval-Augmented Generation) pipelines, including chunking, embedding, vector search, and re-ranking
Develop and optimize Graph RAG architectures, leveraging graph data to enhance LLM responses
Work with graph databases (Neo4j, Spanner Graph, or similar) for schema design and query development
Build and deploy applications on Google Cloud Platform (GCP) including Cloud Run, BigQuery, Pub/Sub, and GCS
Design and maintain Elasticsearch indices and implement search functionality using query DSL
Develop and manage agentic workflows using LangGraph, including multi-agent systems and human-in-the-loop patterns
Collaborate with cross-functional teams to deliver scalable and production-ready AI solutions
Monitor and improve model performance using tools such as Galileo for evaluation and hallucination detection
Required Skills




4+ years of full stack development experience across frontend and backend
Strong proficiency in React, Python, and Node.js
Hands-on experience with GCP services (Vertex AI, Cloud Run, BigQuery, Pub/Sub, Load Balancer, GCS)
Experience working with graph databases (Neo4j, Spanner Graph, or similar)
Good understanding of Elasticsearch (indexing, mappings, query DSL)
Strong knowledge of SQL and data processing (BigQuery / Cloud SQL)
Familiarity with vector databases (Vertex AI Vector Search, Pinecone, pgvector, etc.)
Solid understanding of RAG architectures and LLM integration
Experience consuming LLM APIs, including function calling and structured outputs
Hands-on experience with LangGraph for agent-based workflows
Nice to Have




Experience with graph-based RAG frameworks (Spanner Graph, LlamaIndex Property Graph)
Exposure to NLP pipelines and entity extraction tools (spaCy, GLiNER, etc.)
Knowledge of graph algorithms (PageRank, shortest path, centrality)
Background in ontology or knowledge graph design
Experience with GCP data pipelines
Familiarity with LangChain ecosystem