AI Engineer

AI Engineer

AI Engineer to support critical missions within Peraton's Risk Decision Group. This role builds LLM and document-intelligence capabilities on a greenfield data and AI platform in a high-trust federal environment. Work is hands-on, scoped to a near-term product demonstration, and built to migrate — documented, portable, and transferred to the internal team. Engagement is 1 year with option to extend. Active T5/SSBI clearance required. Top Secret Clearance required.

Responsibilities:

• Build RAG and document-processing pipelines on the Databricks lakehouse — ingestion, OCR of mixed-quality sources, chunking, embedding, and retrieval.
• Build LLM workflows for summarization, structured extraction, and evidence-grounded generation with source attribution.
• Generate synthetic document corpora with the fidelity and quality variation needed for meaningful results.
• Stand up the evaluation harness — retrieval quality, groundedness and hallucination checks, structured-output validity, human-in-the-loop review.
• Report results in numbers.
• Package deliverables as jobs and Asset Bundles, tracked in MLflow, and document everything the internal team needs to own the work.

Required Qualifications:

• U.S. citizenship and active T5/SSBI federally adjudicated clearance required.
• [8]+ years building applied ML/AI or data systems, with demonstrated delivery of LLM and RAG systems you personally built — not notebook demos.
• Hands-on Databricks.
• Document processing at scale: OCR, layout-aware parsing, chunking tradeoffs, poor-quality source handling.
• Local/self-hosted LLM serving — vLLM, TGI, Ollama, llama.cpp, or equivalent — including running open-weight models in an isolated or air-gapped environment without reliance on external API endpoints.
• Structured extraction and grounded generation with source attribution.
• LLM evaluation methodology — you can explain how you measured correctness and what the evaluation missed.
• Privacy-preserving synthetic data generation from CUI, PII, or comparably restricted source data, with an understanding of re-identification risk.
• Strong Python.
• Government or defense contracting experience.

Preferred Qualifications:

• RAG built inside a government or FedRAMP-authorized environment (Azure OpenAI in GCC High, AWS GovCloud, Bedrock within an authorized boundary).
• Direct experience with FedRAMP Moderate, NIST 800-171, CMMC L2, or CUI handling.
• Databricks Vector Search, Mosaic AI Agent Framework and Agent Evaluation, Asset Bundles, MLflow.
• Unity Catalog governance.
• H2O (h2oGPTe, Driverless AI).
• Self-directed execution against a fixed milestone with minimal oversight.
• Honest reporting of model behavior — comfortable saying what an evaluation does and does not establish.
• Collaboration across technical and non-technical teams.
• Clear documentation and active knowledge transfer.