Public Health Analyst

We are seeking an experienced AI/ML Engineer to build and deploy secure, scalable AI solutions for mission-critical initiatives while contributing to proprietary AI infrastructure. You will work with LLMs, RAG, prompt engineering, multi-agent systems, and cloud AI platforms to develop production‑grade machine learning applications.

• Design, implement, and optimize AI/ML solutions using LLMs, RAG, and prompt engineering
  .
• Develop and orchestrate multi-agent systems using Lang Graph and Lang Chain
  .
• Deploy AI solutions across secure cloud environments such as AWS Gov Cloud, Google Gov Cloud, Azure IL5+, Vertex AI, and AWS Bedrock
  .
• Build robust ETL and data pipelines
  , metadata catalogs, and ontologies for AI training and inference.
• Develop and maintain REST APIs and SDK integrations
  .
• Collaborate with product, security, and engineering teams to deliver secure, scalable solutions.
• Follow modern secure coding, Dev Ops, and CI/CD practices.
• Document technical decisions and communicate complex concepts effectively to technical and non‑technical stakeholders.

• Strong Python proficiency for AI/ML development, including REST APIs and SDK integrations.
• Hands‑on production experience with LLMs, RAG, and prompt engineering
  .
• Experience with multi‑agent orchestration
  , tool use, Lang Graph, and Lang Chain.
• Strong knowledge of cloud AI services, including AWS Gov Cloud, Google Gov Cloud, Azure IL5+, Vertex AI, and AWS Bedrock
  .
• Experience building data pipelines, ETL processes, metadata catalogs, and ontologies
  .
• Strong understanding of secure coding and CI/CD practices
  .
• Excellent written and verbal communication skills.

• Experience with enterprise AI platforms such as Anthropic for Gov, OpenAI Enterprise, Gemini Enterprise, or Grok Enterprise
  .
• Knowledge of MCP, metadata catalog platforms, and advanced API development
  .
• Experience working in government, regulated, or security-sensitive cloud environments
  .
• Familiarity with relevant compliance and security standards.