AI/ML Software Engineer - Hybrid ANNAPOLIS, MD

Job DescriptionJob Description The AI/ML Software Engineer will build software tools that incorporate AI/ML techniques to automate narrowly defined tasks with high accuracy, assist internal users with their job functions, and improve the experience external users have when interacting with the Maryland Judiciary. This includes, but is not limited to, RPA work, building or refining chatbots, incorporating AI/ML into reporting tools, building llm agents for knowledge retrieval, deep research, translation, transcription, redaction, document analysis, document generation, agentic coding, and data processing.

a. b. c. 4. Support deployment of AI/ML applications within a hybrid cloud environment Work with containerized applications to ensure reliable deployment and updates. Optimize systems for environments with limited computational resources, including minimal GPU availability General Responsibilities: a. Deliver production-grade systems aligned with defined requirements, while supporting iterative improvement of evolving tools b. c. 5. Document system designs, workflows, and technical decisions as required Stay informed on relevant advancements in AI/ML and apply them where appropriate within project constraints In addition to the overall responsibilities described in Section III.C.1-4, the Offeror's proposed resource(s) will complete the deliverables listed below by Purchase Order year. The estimated level of effort for each deliverable may vary based on its complexity and may be adjusted as needed, including extension beyond the applicable Purchase Order year a. Year 1 (1) Internal Chatbot Refinement: UI improvements, user history & feedback - 240 hours. i Deliverables: Application code + Docker build; user profile & history DB; test cases & privacy/compliance pipeline. "UI improvements, enable user history and feedback " (2) (3) (4) (5) (6) (7) b. Year 2 (1) (2) (3) External Chatbot Development: Initial conversational bot (non-analytical) - 480 hours. i Deliverables: Application code + Docker build; conversation DB; test cases & compliance pipeline; UX/agency scoring. "Goal is conversational but not analytical. Must point users to resources " RPA: Local LLM analysis tools with batching - 240 hours. i Deliverables: Application code; integration documentation; usage & process reporting. Knowledge Retrieval (RAG & Search): Improve vector/hybrid search & case mgmt integration - 520 hours. i Deliverables: Comparative RAG results; agent code/prompts; test pipeline; recommendations for knowledge store updates. Translation: MD-specific terminology & guidelines - 80 hours. i Deliverables: Translation agent code/prompts; test cases & pipeline. Transcription: Refine deployment based on feedback - 160 hours. i Deliverables: Comparative pipeline results; updated code/prompts; test cases & pipeline. Redaction (PII & Sensitive Data): Build detection agent - 240 hours. i Deliverables: Application code; test cases & pipeline for PII/sensitive data identification. Internal Chatbot Refinement: Personalization & workflow integration - 160 hours. i Deliverables: Application code + Docker build; test cases & compliance pipeline. External Chatbot Development: Improvements from feedback - 160 hours. i Deliverables: Application code + Docker build; test cases & compliance pipeline. RPA: Reporting pipelines & analytics; automate tasks - 160 hours. i Deliverables: Application code; integration docs; usage & process reporting.

(4) Knowledge Retrieval: Expand case mgmt integration & permission-based indexing - 240 hours. i Deliverables: Comparative RAG results; agent code/prompts; test pipeline; knowledge store recommendations. (5) (6) (7) (8) (9) c. Year 3 (1) (2) (3) (4) (5) (6) (7) (8) (9) d. Year 4 (1) (2) (3) Deep Research Capabilities: graphRAG for case-statute interaction - 520 hours. i Deliverables: Web/file crawler to graph format; agent code/prompts; test pipeline;