Generative AI Engineer

This position is listed on behalf of a partner company, who manages all applications and next steps. Our partner is looking for a Generative AI Engineer based in United States.

This is an opportunity to build secure, trustworthy generative AI solutions that improve how healthcare organizations access and use authoritative program information. You will design and operate AI-powered decision-support capabilities that allow users to navigate complex statutes, regulations, rules, and guidance through natural language. The role combines hands-on software engineering with expertise in LLMs, retrieval-augmented generation, search, evaluation, and responsible AI. You will work closely with project managers, data engineers, developers, analysts, subject matter experts, and client stakeholders to translate real-world needs into reliable AI solutions. Your work will contribute to systems where accuracy, traceability, security, and responsible use are critical. This role is well suited to an experienced AI engineer who enjoys solving complex problems in a collaborative, mission-driven environment.

Accountabilities

• Design, develop, test, deploy, and maintain generative AI solutions that ground large language model responses in authoritative healthcare program documentation.
• Build and maintain document ingestion pipelines covering parsing, chunking, metadata tagging, embedding generation, and vector or semantic search indexing.
• Translate user needs and stakeholder requirements into effective prompts, context strategies, system requirements, and evaluation criteria in collaboration with cross-functional teams and subject matter experts.
• Implement AI responses that include source citations and direct links to underlying documentation, ensuring that users can trace answers back to authoritative materials.
• Design and implement responsible AI guardrails, including content filtering, scope restrictions, PII and PHI protections, and appropriate refusal handling for out-of-scope questions.
• Develop evaluation frameworks and test datasets to measure retrieval quality, answer accuracy, groundedness, consistency, and overall system performance.
• Continuously monitor, evaluate, and tune AI solutions to improve reliability while balancing accuracy, latency, cost, security, and specific use-case requirements.
• Design AI applications capable of supporting multiple foundation models and providers and evaluate model performance against business and technical requirements.
• Deploy and operate solutions using approved AWS services and within applicable federal security controls, contributing to documentation required for security authorization and AI governance reviews.
• Implement logging, monitoring, and audit trails that support transparency, operational oversight, cost management, and responsible AI governance.
• Write clean, reusable, well-documented code and contribute to code reviews, automated testing, deployment processes, and ongoing system maintenance.
• Collaborate with technical and non-technical stakeholders to communicate AI capabilities, limitations, risks, and performance clearly.
• Stay current with emerging generative AI technologies, foundation models, development frameworks, security practices, and federal AI guidance.

Requirements:

• You have a master’s degree in computer science, data science, engineering, or another relevant technical field.
• You have at least 5 years of experience developing software and cloud-based solutions, including recent hands-on experience designing and deploying LLM or generative AI applications.
• You have strong proficiency in Python and experience working with modern LLM APIs, SDKs, orchestration frameworks, and AI/ML libraries such as Hugging Face, LangChain, LlamaIndex, or equivalent technologies.
• You have hands-on experience designing and deploying generative AI systems involving embeddings, vector databases, and hybrid or semantic search.
• You have experience with AWS AI and data services such as Amazon Bedrock, Amazon OpenSearch, Amazon Kendra, SageMaker, Lambda, or S3.
• You have practical experience with prompt engineering, context engineering, LLM evaluation, and techniques for reducing hallucinations and ensuring responses remain grounded in source material.
• You understand how to evaluate and select foundation models based on factors including accuracy, latency, cost, security, and specific application requirements.
• You have experience working wit…