About Incedo:
Incedo is a global AI and data transformation specialist empowering companies to realize sustainable business impact from their digital investments by delivering ROI from AI@Scale. As a long-term partner for strategy to execution, we operate at the intersection of business and technology. Our integrated services and platforms are built on the foundation of AI & Data, digital engineering, and operations transformation, bringing deep domain expertise and full stack capabilities together. With over 4,000 people in the US, Canada, Latin America and India and a large, diverse portfolio of Fortune 500 enterprises and fast growing clients worldwide, we work across banking & payments, wealth management, telecom, hitech and life sciences.
Please visit the link to know about Incedo: https://www.incedoinc.com/
Full-Stack AI Engineer
Location: Dallas, TX or Tampa, FL or Basking Ridge, NJ
MUST-HAVES
----------
- 4 years of professional software development experience across frontend and backend.
- Proficiency in React, Python, and Node.js.
- 2 years hands-on experience with a graph database (Spanner Graph, Neo4j, or similar) including schema design and query writing.
- Strong experience with Google Cloud Platform (GCP) - Vertex AI, Cloud Run, BigQuery, Pub/Sub, Load Balancer and GCS.
- Comfortable with Elasticsearch for full-text and hybrid search, including index design, mappings, and query DSL.
- Comfortable with SQL (BigQuery / Cloud SQL) and working knowledge of vector databases (Vertex AI Vector Search, pgvector, Pinecone, etc.).
- Solid grasp of RAG architectures: chunking, embedding, vector search, reranking, deduplication and retrieval evaluation.
- Experience consuming LLM APIs (function calling, streaming, structured outputs) - Vertex AI / Gemini or Anthropic / OpenAI.
- Understanding of Graph RAG concepts - using graph structure to augment LLM context, with at least one implementation productionized.
- Hands-on experience building agentic workflows with LangGraph - state machines, multi-agent graphs, tool nodes, and human-in-the-loop patterns.
- Experience using Galileo for LLM evaluation, hallucination detection, and RAG quality monitoring.
NICE-TO-HAVES
-------------
- Experience with Spanner Graph, LlamaIndex Property Graph, or similar graph-native RAG frameworks.
- Familiarity with entity extraction and NLP pipelines for automated graph population (spaCy, Gliner, etc.).
- Exposure to graph algorithms: PageRank, community detection, shortest path, centrality measures.
- Background in ontology or knowledge management work.
- Familiarity with GCP pipelines
- Experience with LangChain / LangGraph.
TECH STACK
----------
Fullstack:
React , TypeScript, Python, Node.js, FastAPI, PostgreSQL / Cloud SQL, Docker, Cloud Run
Graph & Data:
Spanner Graph, Neo4j, Cypher, Memgraph, pgvector, Pinecone, Vertex AI Vector Search, Elasticsearch
AI & Retrieval:
Vertex AI / Gemini, Anthropic / OpenAI APIs, LangGraph, LangChain.
Evaluation & Observability:
Galileo, Google Cloud Logging, Cloud Monitoring
Cloud:
Google Cloud Platform (GCP) - Vertex AI, BigQuery, GCS, Cloud Run