Data & AI Engineer

POSITION TITLE: Data & AI Engineer

LOCATION: Hybrid – Columbia, MD

CLEARANCE: Must be able to obtain a High-Risk Public Trust

COMPANY OVERVIEW

At APV, we’re more than a technology company — we’re a mission-driven powerhouse transforming organizations through advanced technology and human ingenuity. Our expertise spans AI/ML, data architecture, low-code/no-code development, Agile DevSecOps, and cloud services, delivering scalable and meaningful solutions.

In our Emerging Technology Lab, innovation drives progress. Our teams create intelligent chatbots, AI-powered assistants, robotic process automation (RPA), essay graders, and data analytics platforms. If you’re passionate about solving complex challenges and shaping the future, APV is the place for you. Since 2007, we’ve partnered with federal and state agencies to deliver IT, training, and consulting solutions that achieve mission-critical outcomes. Built on accountability, integrity, and quality, we go beyond expectations. With 70+ prime contracts and a proven record of client success, APV continues to grow — and we’re looking for exceptional talent to grow with us.

At APV, we Always Provide Value

POSITION SUMMARY

Provides hands-on data engineering and applied AI/LLM support for a federal proof of concept focused on AI-assisted clinical trial protocol review. The role works under senior technical and domain guidance to prepare protocol data, implement structured data components, configure and test LLM-based extraction workflows, and support traceable retrieval, comparison, and validation within federal approved environments.

DUTIES

· 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, Clinical Data Interchange Standards Consortium (CDISC), Unified Study Definition Model (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 used 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 supporting protocol extraction, historical retrieval, comparison, and source traceability.

· Execute 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.

· Works closely with senior data engineers, clinical protocol SMEs, data standards specialists, architects, and AI/prompt engineers to translate approved requirements into working POC components.

· Participates in prompt and LLM testing, technical working sessions, POC demonstrations, validation activities, and iterative refinement based on client reviewer feedback.

· Supports 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.

· Escalates ambiguous clinical, semantic, or AI-generated results to designated SMEs rather than making independent scientific or regulatory interpretations.

· Contributes practical data and AI engineering skills while developing deeper expertise in clinical protocols, USDM/M11 standards, semantic models, and regulated AI validation.

EDUCATION

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

REQUIRED QUALIFICATIONS

• 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 and working experience with 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.

• Must be able to obtain and maintain a High-Risk Public Trust or equivalent federal client access. This role supports sensitive federal programs and involves elevated access to systems and data.
• Position requires the current ability to obtain and maintain required access without interruption in alignment with long-term program needs.
• Must be authorized 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.

· Experience working with JSON/XML, REST APIs, Git/version control, and cloud or data platforms is beneficial; exposure to AWS, Databricks, or similar platforms.

· Familiarity with RAG, embeddings, vector search/vector databases, semantic retrieval, or grounding techniques is strongly preferred; experience can come from professional, academic, or personal projects.

· Databricks Fundamentals or Generative AI Fundamentals or AI Agent Fundamentals certification

ABOUT APV

APV is an Equal Employment Opportunity employer. All qualified applicants are considered without regard to race, color, religion, sex, national origin, age, disability, genetic information, sexual orientation, gender identity, veteran status, or marital status.