Data & AI Engineer

The Data & AI Engineer will provide hands-on data engineering and applied AI/LLM support for a federal proof of concept centered on AI-assisted clinical trial protocol review. The work includes preparing protocol data, configuring and testing LLM extraction workflows, and enabling traceable retrieval, comparison, and validation in approved environments.

Responsibilities

• Implement and maintain protocol data structures and database components that support extraction, normalization, storage, retrieval, comparison, and reviewer-facing use of ICH M11-aligned and historical protocols.
• Translate approved ICH M11, CDISC, USDM, ontology, metadata, and terminology models into practical schemas, mappings, JavaScript Object Notation (JSON) structures, and data-processing components under guidance from senior standards and architecture SMEs.
• Develop and support ETL/ELT pipelines, Python-based data transformations, and data preparation workflows for protocol content and structured AI outputs while preserving source provenance, metadata, validation status, and reviewer feedback.
• Support development and testing of large language model (LLM) workflows for protocol information extraction, summarization, classification, normalization, and comparison, including prompt configuration and structured-output generation.
• Assist with retrieval-augmented generation (RAG), embeddings, semantic search, vector indexing, evidence retrieval, and context assembly to ground LLM responses in protocol content and approved reference sources.
• Support integration of LLM and data workflows with FDA-furnished Elsa/HALO capabilities and approved data services, including PostgreSQL and/or HALO/Databricks, for evidence caching, analytics, retrieval, and dashboard-ready outputs.
• Develop SQL and Python data-access logic and assist with APIs, JSON/XML processing, data validation, and automation for protocol extraction, historical retrieval, comparison, and source traceability.
• Perform data- and AI-focused testing, including checks for completeness, mapping consistency, retrieval quality, unsupported or hallucinated content, ambiguity, reproducibility, prompt behavior, and regression across approved configurations.
• Document data models, prompts, mappings, test results, interfaces, transformations, implementation decisions, and technical limitations to support client review, knowledge transfer, and iterative Proof of Concept (POC) refinement.
• Work closely with senior data engineers, clinical protocol SMEs, data standards specialists, architects, and AI/prompt engineers to turn approved requirements into working POC components.
• Participate in prompt and LLM testing, technical working sessions, POC demonstrations, validation activities, and iterative refinement based on client reviewer feedback.
• Support implementation within provided platforms and approved data environments; the base effort is a proof of concept and does not require independent ownership of a production platform.
• Escalate ambiguous clinical, semantic, or AI-generated results to designated SMEs instead of making independent scientific or regulatory interpretations.
• Build practical data and AI engineering capability while developing deeper expertise in clinical protocols, USDM/M11 standards, semantic models, and regulated AI validation.

Requirements

• 3-5 years of experience in data engineering, software development, data science, AI/ML, analytics, or a related technical role.
• Hands-on experience with Python for data processing, automation, API integration, or AI/ML workflows.
• Data modeling experience and practical working knowledge of relational databases, XML and JSON structure.
• Practical exposure to generative AI and large language models, including prompt development, LLM APIs, structured outputs, evaluation, or application development using modern AI frameworks.
• Ability to obtain and maintain a High-Risk Public Trust or equivalent federal client access.
• Current ability to obtain and maintain required access without interruption in alignment with long-term program needs.
• Authorization to work in the United States without employer sponsorship now or in the future.

Preferred Qualifications

• Working knowledge of SQL and relational databases such as PostgreSQL, Oracle, or SQL Server; exposure to data modeling, ETL/ELT, metadata, or data-quality practices.
• Beneficial exposure to JSON/XML, REST APIs, Git/version control, and cloud or data platforms; exposure to AWS, Databricks, or similar platforms.
• Strong preference for familiarity with RAG, embeddings, vector search/vector databases, semantic retrieval, or grounding techniques (professional, academic, or personal projects acceptable).
• Databricks Fundamentals or Generative AI Fundamentals or AI Agent Fundamentals certification.

Technologies

• Python, JavaScript Object Notation (JSON), XML, SQL, ETL/ELT, PostgreSQL
• Elsa/HALO, HALO, Databricks
• ICH M11, Clinical Data Interchange Standards Consortium (CDISC), Unified Study Definition Model (USDM)
• RAG, embeddings, semantic search, vector indexing
• Large language model (LLM), APIs, REST APIs
• Git/version control

Location and Clearance

• Location: Hybrid, Columbia, MD
• Clearance: Must be able to obtain a High-Risk Public Trust

Education

Bachelor’s degree in computer science, data science, computer engineering or related field.