Senior AI Data Engineer

Apexon; New Jersey; On-site; USD 140,000 - 210,000; Full time

Job summary

Apexon is seeking a Senior Data Analytics & Knowledge Engineer to join our rapidly growing AI and Data Engineering team in the Life Sciences and Healthcare domain. This hands-on role focuses on building AI-ready data foundations to enable intelligent agents that retrieve, reason over, and generate accurate responses from enterprise knowledge sources.

The role involves designing scalable data pipelines, constructing knowledge graphs and semantic models, and delivering production-ready RAG and

Qualifications

• 8+ years in Data Eng, Knowledge Eng, or AI Eng.
• Proficient in Python and SQL.
• Hands-on with graph databases like Neptune or Neo4j.
• Experience building LLM apps and RAG pipelines on AWS.

Responsibilities

• Design and build scalable data ingestion and transformation pipelines using Python and AWS services.
• Create AI-ready datasets from structured and unstructured enterprise data.
• Build and manage knowledge graphs, ontologies, taxonomies, semantic models.
• Develop graph-based retrieval solutions with Neptune or Neo4j.
• Build Retrieval-Augmented Generation (RAG) pipelines with vector search.
• Implement semantic chunking, embeddings, and grounding for LLM apps.
• Develop LLM-powered apps using Bedrock, prompts, and RAG frameworks.
• Create Text-to-SQL capabilities for natural language querying over datasets.
• Collaborate with AI Engineers, Solution Architects, and Data/ML teams to improve retrieval quality.

Skills

Data Engineering

Knowledge Engineering

AI Engineering

Python

SQL

Graph Databases

RDF/OWL

Semantic Models

RAG

Bedrock

LangChain

AWS

Tools

Amazon Neptune

Neo4j

Amazon Bedrock

OpenSearch

Job description

Apexon is looking for a Senior Data Analytics & Knowledge Engineer to join our growing AI and Data Engineering team. This is a hands‑on engineering role focused on building AI‑ready data foundations for next‑generation AWS Agentic AI applications in the Life Sciences and Healthcare domain.

You'll work at the intersection of Data Engineering, Knowledge Graphs, Semantic AI, and Generative AI, enabling intelligent agents to retrieve, reason over, and generate accurate responses from enterprise knowledge.

What You'll Do

• Design and build scalable data ingestion and transformation pipelines using Python and AWS services.
• Create AI‑ready datasets from structured and unstructured enterprise data.
• Build and manage knowledge graphs, ontologies, taxonomies, and semantic models to represent business entities and relationships.
• Develop graph‑based retrieval solutions using Amazon Neptune (or Neo4j experience).
• Build Retrieval‑Augmented Generation (RAG) pipelines using vector search technologies such as Amazon OpenSearch Service.
• Implement semantic chunking, embeddings, metadata enrichment, and grounding strategies for LLM applications.
• Develop LLM‑powered applications using Amazon Bedrock, prompt engineering, and RAG frameworks.
• Build Text-to-SQL capabilities for natural language querying over governed datasets.
• Work with AWS Glue Data Catalog, Amazon S3/S3 Tables, and Apache Iceberg to create discoverable and governed data assets.
• Collaborate with AI Engineers, Solution Architects, and Data/ML teams to improve retrieval quality, lineage, and production readiness.

Required Skills

• 8 years of experience in Data Engineering, Knowledge Engineering, or AI Engineering.
• Strong programming experience in Python and SQL.
• Hands‑on experience with Amazon Neptune or Neo4j.
• Experience designing Knowledge Graphs, ontologies, and semantic data models.
• Good understanding of RDF, OWL, SKOS, and Turtle (.ttl) files.
• Experience building RAG applications using vector search and embeddings.
• Hands‑on experience with Amazon Bedrock and AWS AI services.
• Experience with AWS Glue, Amazon S3, Apache Iceberg, and cloud data architectures.
• Experience using LangChain, LlamaIndex, or similar GenAI orchestration frameworks.
• Understanding of Text-to-SQL implementation and LLM integration patterns.

Nice to Have

• Experience with Databricks or lakehouse architectures.
• Exposure to Life Sciences, Healthcare, or Pharmaceutical data.
• Experience with metadata management, data lineage, governance, and AI‑ready data preparation.
• Familiarity with Strands Agents or agentic AI frameworks.