Role Overview:
As an AI/ML Engineer for CTEC, you will develop Agentic AI systems designed to automate and optimize health benefits determinations for the Office of Personnel Management (OPM). Unlike traditional "black-box" models, your work will focus on marrying the reasoning capabilities of Large Language Models (LLMs) with deterministic, rule-driven patterns to ensure accuracy, auditability, and compliance in complex decision-making workflows.
Duties and Responsibilities:
- Agentic System Architecture: Design and deploy autonomous AI agents capable of multi-step reasoning, tool-use, and self-correction to navigate complex federal benefit policies.
- Deterministic Logic Integration: Develop "Guardrail" layers that synchronize probabilistic LLM outputs with rigid business rules, ensuring benefit determinations adhere strictly to legal and regulatory frameworks.
- RAG & Knowledge Engineering: Implement advanced Retrieval-Augmented Generation (RAG) solutions, utilizing layout-aware parsing to extract information from dense manuals/documentation and unstructured data.
- Hybrid Model Development: Design and evaluate machine learning models that support both data-driven predictions and symbolic/rule-based automation.
- MLOps & Agent Monitoring: Deploy models into cloud environments with a focus on LLM-specific observability (tracing reasoning loops, monitoring for hallucinations, and detecting data drift in logic).
- Auditability & Explainability: Ensure every AI-driven determination has a clear, human-readable "audit trail" or reasoning chain that justifies the outcome based on source documentation.
- Collaboration: Work alongside solution architects and business stakeholders to translate complex health insurance policies into executable AI logic.
Skills & Work Experience:
- Professional Experience: 5+ years in Machine Learning or Data Science, with at least 2 years of hands-on experience with LLM orchestration and Generative AI frameworks.
- Agentic Frameworks: Proficiency with tools such as LangChain, LangGraph, CrewAI, or Semantic Kernel for building multi-step agent workflows.
- Core Development: Strong proficiency in Python and experience with standard frameworks (PyTorch, TensorFlow, or Scikit-learn)
- Data Engineering: Strong SQL skills and experience with distributed data processing (Spark/PySpark) to handle large-scale enterprise data.
- Analytical Rigor: Ability to debug non-deterministic systems and implement rigorous evaluation frameworks (e.g., RAGAS, LLM-as-a-judge) data platforms.
Preferred:
- Experience with Azure Machine Learning, Azure AI services, or similar cloud AI platforms.
- Experience implementing Generative AI, LLM, or RAG-based solutions.
- Experience supporting federal IT modernization or data transformation programs.
- Familiarity with healthcare, insurance, or benefits administration data environments.
- Experience applying data governance, privacy, and security best practices in AI/ML solutions.
Education:
Bachelor’s degree in Computer Science, Data Science, Engineering, or a related discipline. Master’s degree preferred. Equivalent professional experience will be considered in lieu of a degree.
Clearance:
Must be a U.S. citizen and be able to obtain an OPM Public Trust clearance.