Applied AI Engineer – Global Health, AI

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

📋 Description

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

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

• Build tools for natural language analysis of survey data.

• Develop tools for multilingual questionnaire translation.

• Create field support tools for interviewers and supervisors.

• Construct evaluation harnesses and establish acceptance criteria in collaboration with technical and survey experts.

• Generate test sets from expert-generated ground truth and conduct non-inferiority comparisons.

• Distribute tasks across models based on reasoning complexity, volume, cost, latency, and data residency requirements.

• Oversee inference costs by tracking token usage, managing context limits, utilizing prompt caching, and implementing batch processing.

• Integrate models with data services and full-stack applications.

• Employ agentic coding tools for the production, review, testing, and ownership of software.

• Monitor production systems and perform thorough error analysis.

• Report both positive and negative outcomes.

• Document methodologies and results for public dissemination.

• Assist in transferring tools to partner-country institutions.

⛳️ Requirements

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

• At least 4 years of professional software development experience, specifically in building LLM-powered systems that are operational in production environments.

• U.S. citizenship is required due to federal government contract stipulations.

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

• Practical experience utilizing frontier-model APIs, including tool usage and retrieval-augmented generation.

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

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

• Background in building and deploying applications on a significant cloud platform, such as AWS, Azure, or Google Cloud.

• Experience with agentic coding tools such as Claude Code, OpenAI Codex, Cursor, Antigravity, or GitHub Copilot in agent mode.

• Knowledge of agent frameworks and AI evaluation tools.

🏝️ Benefits

• Opportunity for remote work within the United States.

• Occasional travel may be required.

• Reasonable accommodations provided for individuals with disabilities, veterans, and those with sincerely held religious beliefs.

• Commitment to equal opportunity employment.

• Confidential accommodation support available throughout the application and employment process.