About the job
The AI/ML Engineer - Generative AI will play a key role in designing, building, and scaling enterprise grade GenAI solutions across Optum Technology platforms. This role focuses on large language models (LLMs), retrieval augmented generation (RAG), and agentic AI patterns that power real time proactive assist support, automation, and intelligent user experiences. You will partner closely with AI Architects, Platform Engineers, Cloud Engineers, and Product teams to operationalize GenAI capabilities in production-balancing innovation with responsible AI, reliability, performance, and regulatory requirements in a healthcare environment. This role is ideal for engineers who enjoy working on Google tech stack at the intersection of LLMs, system design, and real world business workflows.
Responsibilities
Design, develop, and deploy Generative AI solutions using large language models (LLMs) and enterprise AI platforms
Implement and optimize retrieval augmented generation (RAG) pipelines, including document ingestion, embeddings, ranking, and context assembly
Build prompting, orchestration, and agentic workflows to support multi step reasoning, tool use, and automation
Fine tune, evaluate, and continuously improve GenAI models for accuracy, latency, cost, and safety
Partner with AI Architects and Cloud Engineers to integrate GenAI solutions into production systems and enterprise platforms
Implement model evaluation, guardrails, monitoring, and feedback loops to support responsible and explainable AI usage
Troubleshoot GenAI system issues across prompts, retrieval, model behavior, and downstream integrations
Document GenAI architectures, prompts, evaluation strategies, and operational runbooks to support audits and long term maintainability
Stay current with emerging GenAI patterns, tools, and frameworks and assess applicability to enterprise use cases
Qualifications
Minimum
Bachelor's degree or 4+ years of equivalent professional experience
3+ years of experience in AI/ML engineering, with hands on experience building Generative AI solutions
3+ years of experience in Python for AI/ML and GenAI development
2+ years of experience deploying AI solutions on cloud platforms, Google Cloud Platform (GCP)
Solid experience working with large language models (e.g., Gemini, GPT class models)
Proven understanding of prompt engineering, RAG architectures, embeddings, and vector search
Proven understanding of model evaluation, hallucination mitigation, and AI safety considerations
Ability to collaborate effectively with cross functional engineering, product, and architecture teams
Preferred
Experience building production GenAI systems in a regulated or large scale enterprise environment
Demonstrated familiarity with agentic frameworks, tool calling patterns, or workflow orchestration for LLMs
Experience integrating GenAI into CRM or enterprise applications (e.g., Salesforce, Pega)
Proven knowledge of Responsible AI, governance, and compliance practices
Experience with MLOps / LLMOps, model monitoring, and feedback driven improvement
Experience in healthcare, payer, or clinical domains
Proven solid communication skills with the ability to explain GenAI concepts to non technical stakeholders