Applied AI Engineer — Global Health & AI (REMOTE ROLE)
Company: ICF
Location: Reston, VA (Remote)
Type: Full-time
Remote: Yes
Posted: 2026-11-17
About this role
Description
Applied AI Engineer — Global Health & AI
ICF's Global Health and Development (GHD) line of business, part of the Health, People, and Human Services (HPHS) Group, is seeking an
Applied AI Engineer
to build frontier-model systems for various global health and survey programs. This role will support the development of AI-enabled tools that draft survey reports, let researchers and policymakers analyze data in natural language, translate questionnaires into low-resource languages, and support interviewers and data quality in the field. No tool is adopted unless it matches or beats the expert-led process it replaces. You will build the prompting, agent, and pipeline layer across the program. You will also build the evaluation harnesses that show whether each tool actually works, judged against ground truth produced by some of the most experienced survey methodologists in the world.
*This position can be remote within the United States, with occasional travel.*
*It is contingent upon award of program funding.*
Key Responsibilities
- Design and build LLM pipelines and agents for survey workflows, including:
- an AI-assisted data-to-report pipeline
- natural-language analysis of survey data
- multilingual questionnaire translation
- field support tools for interviewers and supervisors
- Build evaluation harnesses as first-class deliverables. Work with the Technical Lead and survey experts to define acceptance criteria before the work is judged. Build test sets from expert-produced ground truth and run the non-inferiority comparisons that decide whether a tool moves forward.
- Route work across models based on reasoning complexity, volume, cost, latency, and data-residency requirements.
- Manage inference cost by tracking token usage, context limits, prompt caching, and batch processing, and account for these operating costs in model-selection decisions.
- Connect models to data services and to the applications built by full stack...