AI Engineer

GDH; North Carolina; Remote; USD 110,000 - 116,000; Full time

Job summary

GDH is seeking a contract AI Engineer to develop RAG and document-processing pipelines in a federal context. The role focuses on building scalable, secure AI on a greenfield platform and delivering a near-term product demonstration.

You will implement privacy-preserving synthetic data, manage deployments of open-weight LLMs, and collaborate across teams to meet security requirements. Remote work within the United States is allowed.

Qualifications

• 8+ years in ML/AI or data systems with deliverable LLM/RAG projects beyond notebooks.
• Hands-on Databricks development, deployment and management.
• Processing data at scale including OCR and parsing of mixed-quality sources.
• Privacy-preserving synthetic data from sensitive sources; awareness of re-identification risks.
• Proficiency in Python and related data science tools.
• Experience in government or defense contracting environments.

Responsibilities

• Develop retrieval-augmented generation (RAG) and document-processing pipelines using Databricks lakehouse, OCR, chunking, embedding and retrieval methods.
• Build LLM workflows for summarization, structured data extraction, and evidence-grounded text generation with source attribution.
• Generate synthetic document corpora that meet fidelity and quality variation criteria.
• Establish evaluation frameworks for retrieval quality, grounding, hallucination rates and structured output validity.
• Package deliverables as jobs and asset bundles; track progress with MLflow; maintain comprehensive documentation.
• Implement privacy-preserving synthetic data generation techniques for sensitive sources and re-identification risk awareness.
• Ensure secure local deployment of open-weight LLMs (e.g., TGI, Ollama, llama.cpp) in isolated or air-gapped environments.
• Collaborate with cross-functional teams to integrate AI solutions within federal security and compliance standards.
• Monitor and report model performance metrics with clear insights for evaluation and improvement.

Skills

Python

Databricks

RAG systems

LLM workflows

OCR processing

Data extraction

Security/compliance

Tools

vLLM

TGI

Ollama

llama.cpp

Job description

Role Summary

This contract AI Engineer role involves developing advanced language models and document intelligence capabilities within a high-trust federal environment. The position requires hands‑on work on a greenfield data and AI platform, focusing on building scalable, secure, and reliable AI solutions. The engineer will contribute to a near‑term product demonstration, with scope for knowledge transfer and future internal team ownership, operating on a one‑year contract with an option to extend.

Responsibilities

• Develop retrieval‑augmented generation (RAG) and document‑processing pipelines utilizing Databricks lakehouse ingestion, OCR, chunking, embedding, and retrieval methods.
• Build large language model (LLM) workflows for summarization, structured data extraction, and evidence‑grounded text generation with source attribution.
• Generate synthetic document corpora that meet fidelity and quality variation criteria for meaningful AI outputs.
• Establish evaluation frameworks to assess retrieval quality, grounding, hallucination rates, and structured output validity, including human‑in‑the‑loop review processes.
• Package deliverables as jobs and asset bundles, track progress using MLflow, and maintain comprehensive documentation for internal team ownership.
• Implement privacy‑preserving synthetic data generation techniques for sensitive or restricted data sources, understanding re‑identification risks.
• Ensure secure local deployment of open‑weight LLMs (such as TGI, Ollama, llama.cpp) in isolated or air‑gapped environments.
• Collaborate with cross‑functional teams to integrate AI solutions within the federal environment, adhering to security and compliance standards.
• Monitor and report model performance metrics, providing clear, actionable insights for evaluation and improvement.

Qualifications

• This position requires eligibility for a U.S. Government security clearance. In accordance with federal law, U.S. citizenship is required. (Active T5/SSBI federally adjudicated security clearance).
• Minimum of 8 years of experience in building applied ML/AI or data systems, with demonstrated delivery of personal LLM and RAG systems beyond notebook prototypes.
• Extensive hands‑on experience with Databricks platform, including development, deployment, and management.
• Proven expertise in processing data at scale, including OCR, parsing of mixed-quality sources, and handling poor source quality.
• Practical knowledge of local/self‑hosted LLM serving environments such as vLLM, TGI, Ollama, llama.cpp, or similar.
• Strong background in structured data extraction, grounded generation with source attribution, and model evaluation methodologies.
• Experience generating privacy‑preserving synthetic data from sensitive sources, with awareness of re‑identification risks.
• Proficiency in Python programming and related data science tools.
• Prior experience working within government or defense contracting environments.

Publishing Pay Range: $80.00 – $84.00 hourly

This is a fully remote role and can be performed from any approved location within the United States.