Senior Data Engineer (AI/GenAI)

Linchpin Software is growing, and we’re looking for a Senior Data Engineer to build the pipelines and data architecture behind an in-house AI and GenAI analytic platform. This is not a bolt-on chatbot. You’ll engineer the vector, graph, and relational data layers that let multi-model reasoning, entity resolution, and retrieval run against structured and unstructured mission data, with full provenance and citation behind every answer.

The platform is custom-built, runs in air-gapped and hybrid environments on locally hosted GPU infrastructure, and serves analysts who need results they can trace back to the source. You’ll design the ingest, shape the schemas, and make sure the data feeding the models is fast, governed, and defensible.

We build software differently. Our engineers use AI-assisted development tools (Claude Code, Codex, GitLab Duo) every day to design, code, test, and debug faster. You’ll spend your time solving hard data problems, not writing boilerplate.

What You’ll Do:

• Build automated ETL pipelines for schema-aligned ingestion and normalization of diverse structured, semi-structured, and unstructured data
• Engineer and orchestrate vector, graph, and relational databases (LanceDB, lance graph, PostgreSQL) powering retrieval and reasoning
• Implement Named Entity Recognition (NER), contextual entity extraction, and entity resolution at scale
• Support multi-step retrieval, structured output generation, and deep source citation so every analytic result is traceable
• Enforce Attribute Based Access Control (ABAC) at the data layer and track end-to-end data lineage and provenance
• Design and optimize enterprise relational databases and set standards for operations, performance, and security
• Integrate reasoning components, retrieval systems, databases, and GenAI services across the stack
• Mentor junior engineers and contribute to cross-team data standards

• Active Top Secret clearance
• Bachelor’s degree
• 8+ years of experience in data engineering, database design, or a related field
• Strong relational database design, SQL, and ETL/ELT skills
• Strong Python skills and experience building production data pipelines
• Experience working with structured, semi-structured, and unstructured data
• Experience improving data workflows, performance, and security
• Ability to work full-time, on-site in Chantilly, VA (20151)

Preferred:

• Vector or graph databases and retrieval-augmented generation (RAG) pipelines
• AI/GenAI engineering: multi-model orchestration, computer vision, or temporal, spatial, and geographic analytics
• Backend and middleware development (FastAPI, Temporal.io, TypeScript, React)
• Container orchestration and distributed systems (Docker, Kubernetes)
• Air-gapped, hybrid, or on-premise environments and locally hosted GPU servers
• Multi-tenant Cross-Domain Solutions (CDS)
• Federal or secure multi-enclave environments
• High-performance computing, data modeling, warehousing, and performance tuning

What You’ll Gain:

• A custom AI platform you help architect, not a legacy system you inherit
• Hands-on GenAI and multi-model engineering experience that is hard to get in a cleared environment
• Real ownership of the data architecture, from ingest through analytic output
• A small, collaborative team on a stable, long-term mission program
• Competitive compensation and benefits