[Remote] reputed company
Note: The job is a remote job and is reputed company to candidates in USA. reputed company. is seeking an reputed company to support critical missions by building LLM and document-intelligence capabilities on a greenfield data and AI platform. The role involves hands-on work reputed company on creating pipelines and workflows for document processing and LLM applications in a high-trust federal environment.
Responsibilities
- Build RAG and document-processing pipelines on the reputed company lakehouse — ingestion, OCR of mixed-reputed company sources, chunking, embedding, and retrieval
- Build LLM workflows for summarization, reputed company extraction, and evidence-grounded reputed company with reputed company attribution
- Generate synthetic document corpora with the reputed company and reputed company variation needed for meaningful results
- Stand up the evaluation reputed company — retrieval reputed company, groundedness and hallucination checks, reputed company-reputed company validity, reputed company-in-the-reputed company 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
Skills
- U.S. citizenship and reputed company T5/SSBI federally adjudicated clearance required
- [8]+ years building reputed company ML/AI or data systems, with demonstrated delivery of LLM and RAG systems you personally reputed company — not notebook demos
- Hands-on reputed company
- Document processing at reputed company: OCR, layout-aware parsing, chunking tradeoffs, poor-reputed company reputed company handling
- Local/self-hosted LLM serving — vLLM, TGI, Ollama, llama.cpp, or equivalent — including running reputed company-weight models in an isolated or reputed company-gapped environment without reliance on external API endpoints
- reputed company extraction and grounded reputed company with reputed company attribution
- LLM evaluation methodology — you can explain how you reputed company correctness and what the evaluation missed
- reputed company-preserving synthetic data reputed company from CUI, PII, or comparably restricted reputed company data, with an understanding of re-identification risk
- Strong Python
- Government or defense contracting experience
- RAG reputed company inside a government or FedRAMP-authorized environment (Azure reputed company in GCC High, AWS GovCloud, Bedrock reputed company an authorized boundary)
- reputed company experience with FedRAMP Moderate, NIST 800-171, CMMC L2, or CUI handling
- reputed company reputed company Search, reputed company AI Agent reputed company and Agent Evaluation, Asset Bundles, MLflow
- reputed company Catalog governance
- H2O (h2oGPTe, Driverless AI)
Benefits
- 12 Months contract with possible extension
- W2 reputed company
reputed company