AI Engineer

The Opportunity: 

Design and build robust knowledge frameworks enabling AI systems to dynamically interact with structured and unstructured public health data, facilitating real-time insights and decision-making support. Leverage knowledge of the design and implementation of base architectures, data modeling for AI agents, Memory and State Management, and construction of RAG Pipeline Design to facilitate multi-modal data integration, partnering closely with data engineers on data pipeline coordination. Lead performance optimization of retrieval processes for public health use cases and define rigorous data quality and curation standards. Collaborate with AI teams and maintain thorough documentation of data architecture. Ensure compliance with data privacy standards, anonymization protocols, and ethical guidelines critical to public health data management.

You Have:

• Experience in Generative AI, including work with Large Language Models (LLMs)

• Experience with Python programming language and with the deployment and integration of AI solutions on the cloud

• Experience in document processing workflows, including ingestion and transformation of formats, such as PDF, Word, and HTML, and development of vector databases for semantic search and retrieval

• Experience designing and implementing Retrieval-Augmented Generation (RAG) architectures for production environments

• Experience working with AI-assisted coding tools

• Knowledge of containerization and orchestration technologies, including Docker or Kubernetes, and implementation of CI/CD pipelines for AI and ML workflows

• Knowledge of an Agentic AI framework, including Google ADK, Strands, Pydantic-AI, LangGraph, Microsoft Agent Framework, or OpenAI Agents SDK

• Ability to review, 'sniff-check,' and debug AI-generated code for security and correctness

• Ability to obtain and maintain a Public Trust or Suitability/Fitness determination based on client requirements

• Bachelor’s degree

Nice If You Have:  

• Experience in full-stack development or deployment of end-to-end machine learning applications

• Experience fine-tuning large-scale models for domain-specific tasks in secure or fully isolated, air-gapped environments

• Experience designing Human-in-the-Loop (HITL) workflows and interfaces that allow for manual verification of autonomous agent actions in high-stakes environments

• Experience with MLOps practices, including testing, evaluation, and deployment of AI and ML solutions in production environments

• Knowledge of AI evaluation and benchmarking frameworks, including RAGAS or DeepEval to quantify model performance, mitigate hallucinations, and ensure output quality

• Ability to work with open-source models and host them in fully isolated environments, ensuring security and compliance

Vetting:

Applicants selected will be subject to a government investigation and may need to meet eligibility requirements of the U.S. government client.