Applied AI Engineer – Global Health

This is a fully remote position, open to applicants in United States.

📋 Description

• Design and develop LLM pipelines and agents tailored for survey workflows.

• Create AI-enhanced data-to-report pipelines.

• Facilitate natural-language analysis of survey data.

• Develop tools for multilingual questionnaire translation.

• Create field-support tools for interviewers and supervisors.

• Construct evaluation harnesses that include acceptance criteria, expert-generated ground truth, test sets, automated and manual grading, regression testing, and ship/no-ship determinations.

• Allocate work across models based on reasoning complexity, workload, cost, latency, and data-residency requirements.

• Manage inference costs through token usage monitoring, context limits, prompt caching, and batch processing.

• Connect models to data services and comprehensive applications.

• Utilize agentic coding tools to produce, review, test, and maintain production software.

• Oversee production systems, perform error analysis, and report both positive and negative outcomes.

• Document methodologies and results for public dissemination.

• Transfer tools to partner-country institutions for autonomous operation.

• Collaborate with the Technical Lead, survey specialists, funders, and partner-government personnel.

⛳️ Requirements

• Bachelor's degree in Computer Science, Engineering, or a related discipline, or equivalent work experience.

• At least 4 years of professional software development experience, including the creation of LLM-powered systems utilized by real users in a production environment.

• U.S. citizenship is mandated by federal government contracts.

• Must be eligible to work in the United States without the need for sponsorship.

• Proficiency in Python or another contemporary programming language, such as JavaScript/TypeScript or Go.

• Practical experience with frontier-model APIs, including tool use and retrieval-augmented generation.

• Experience in designing LLM evaluations, encompassing test-set development, automated and manual grading, regression testing, and ship/no-ship decisions.

• Familiarity with LLM cost, latency, and model-selection trade-offs.

• Experience with building and deploying applications on AWS, Azure, Google Cloud, or another major cloud service provider.

• Experience in using agentic coding tools to specify, review, test, and manage production code.

• Experience with agent frameworks and AI evaluation tools.

• Preferred: experience with subject-matter-expert ground truth, structured or tabular data, multilingual or low-resource-language NLP, open-weight models, sensitive or regulated data, model governance, global health, public service, or technical writing.

• Ability to articulate AI trade-offs clearly to both technical and non-technical audiences.

• Ability to collaborate across various disciplines, cultures, time zones, and organizational levels.

• Ability to candidly communicate uncertainty, limitations, and negative results.

• Self-motivated and capable of contributing effectively with minimal direct supervision.

🏝️ Benefits

• Occasional travel opportunities.

• Reasonable accommodations for disabilities, religious purposes, disabled veterans, individuals with disabilities, and sincerely held religious beliefs.

• Equal opportunity employment practices.

• Benefit offerings as referenced under the Transparency in Coverage Act.