Senior AI or ML Engineer - Conversational AI, Bot Development

Optum is a global organization that delivers care, aided by technology to help millions of people live healthier lives. The work you do with our team will directly improve health outcomes by connecting people with the care, pharmacy benefits, data and resources they need to feel their best. Here, you will find a culture guided by inclusion, talented peers, comprehensive benefits and career development opportunities. Come make an impact on the communities we serve as you help us advance health optimization on a global scale. Join us to start Caring. Connecting. Growing together.

Primary Responsibilities

• Conversational AI and Bot Development
• Design, develop, test, deploy, and continuously improve enterprise-grade chatbots, voice bots, virtual assistants, and copilots
• Build multi-turn conversational experiences incorporating intent recognition, entity extraction, dialogue and session management, context retention, disambiguation, personalisation, and task completion
• Develop conversational journeys across chat, voice, web, mobile, contact-centre, and enterprise collaboration channels
• Implement handling for interruptions, corrections, ambiguous requests, incomplete information, fallbacks, escalation, and human-agent hand-off
• Integrate bots with enterprise APIs, knowledge repositories, workflow platforms, identity services, contact-centre solutions, and backend applications
• Apply conversation-design principles to deliver natural, accessible, consistent, and task-oriented user experiences
• Agentic AI Solution Design and Implementation
• Design and build agentic bots capable of reasoning, planning, function calling, tool usage, memory management, knowledge retrieval, API interaction, and multi-step workflow execution
• Develop single-agent and multi-agent solutions using frameworks such as Google ADK, LangGraph, LangChain, Semantic Kernel, AutoGen, CrewAI, or similar technologies
• Implement orchestration patterns including supervisor, router, planner-executor, specialist-agent, sequential, parallel, and human-in-the-loop workflows
• Define agent instructions, tools, state, memory, permissions, and operational boundaries to support predictable and secure behaviour
• Implement approval checkpoints, restricted tool access, retry and timeout policies, action validation, auditability, and safe termination
• Build graceful fallback and escalation mechanisms when an agent lacks sufficient information, confidence, permissions, or capability
• Google Conversational AI and Agent Ecosystem
• Design and optimise conversational experiences using Google GECX, including flows, intents, entities, routes, fulfilment, parameters, events, integrations, and environment configuration
• Develop and orchestrate AI agents using Google ADK, including agent definitions, tools, sessions, state, memory, workflow coordination, and evaluation
• Integrate Google conversational AI solutions with Gemini models, enterprise knowledge sources, APIs, webhook services, and backend applications
• Develop reusable bot components, agent templates, tools, connectors, conversation patterns, prompts, and evaluation assets
• Troubleshoot issues across conversation flows, agent orchestration, fulfilment services, session state, authentication, APIs, channels, and production telemetry
• Hands-On Engineering and Cloud Development
• Contribute directly to bot configuration, software development, prompt engineering, agent orchestration, integration, testing, debugging, and production delivery
• Build fulfilment services, APIs, microservices, reusable libraries, and connectors using Python, Java, Spring Boot, or comparable technologies
• Integrate bots and agents with REST APIs, databases, event streams, workflow engines, identity providers, CRM platforms, claims systems, and knowledge repositories
• Build secure, scalable, cloud-native AI solutions, preferably using Google Cloud, while supporting Azure-based environments where required
• Apply modular design, source control, automated testing, code reviews, observability, documentation, and secure development practices
• Ensure solutions meet enterprise requirements for reliability, privacy, security, scalability, resiliency, and operational readiness
• DevOps, Governance and Operational Readiness
• Build CI/CD pipelines for bot configurations, prompts, agent definitions, orchestration code, fulfilment services, infrastructure, and evaluation assets
• Support containerised deployments using Docker, Kubernetes, Google Kubernetes Engine, Azure Kubernetes Service, or comparable platforms
• Implement quality gates, security scanning, configuration validation, environment promotion, monitoring, rollback, and release governance
• Establish logging, distributed tracing, dashboards, alerting, operational runbooks, incident triage, and recovery procedures
• Apply DevOps, MLOps, and LLMOps practices to support controlled and continuous improvement
• Implement authentication, authorisation, least-privilege access, secrets management, data protection, safe tool execution, and auditability
• Ensure alignment with enterprise security, privacy, compliance, and Responsible AI requirements

Technical Leadership

• Lead and mentor engineers delivering conversational AI, GenAI, and agentic bot solutions while remaining actively hands-on
• Provide technical direction, conduct code and design reviews, and guide architecture, platform, and implementation decisions
• Establish reusable standards, reference architectures, development guidelines, review checklists, and adoption playbooks
• Build team capability in Google GECX, Google ADK, conversation design, agent orchestration, RAG, testing, LLMOps, cloud development, and Responsible AI
• Communicate technical options, risks, dependencies, and trade-offs clearly to business and technology stakeholders
• Comply with all applicable Company policies, procedures, and business directives, changes including those relating to work location, team assignments, work schedules, and flexible work arrangements

Required Qualifications

• Bachelor's or Master's degree in Computer Science, Engineering, Artificial Intelligence, Machine Learning, Data Science, or a related technical field; equivalent practical experience will also be considered
• 8+ years of experience in software engineering, conversational AI, AI/ML engineering, platform engineering, or distributed systems
• Hands-on experience building AI agents using reasoning, planning, function calling, tools, memory, APIs, and multi-step workflows
• Demonstrable hands-on experience developing production-grade chatbots, voice bots, virtual assistants, copilots, or conversational AI applications
• Experience with at least one agent framework such as Google ADK, LangGraph, LangChain, Semantic Kernel, AutoGen, CrewAI, or equivalent
• Experience integrating bots or agents with enterprise APIs, backend applications, databases, authentication services, workflow engines, and knowledge sources
• Experience implementing RAG pipelines, including ingestion, chunking, embeddings, vector search, semantic retrieval, reranking, grounding, and response generation
• Experience developing backend fulfilment or integration services; Java or Spring Boot experience is beneficial
• Experience with cloud-native development on Google Cloud, Azure, or another major cloud platform
• Experience with Docker, Kubernetes, CI/CD pipelines, logging, monitoring, distributed tracing, and production troubleshooting
• Experience testing conversational and agentic applications across unit, integration, regression, end-to-end, prompt, retrieval, tool, and workflow scenarios
• Solid experience with multi-turn conversations, intents, entities, dialogue flows, context management, session state, fulfilment, fallbacks, and escalation
• Solid understanding of prompt engineering, agent instructions, tool definition, context management, model evaluation, guardrails, and Responsible AI controls
• Proficiency in Python and solid knowledge of APIs, microservices, asynchronous processing, automated testing, observability, and scalable system design
• Proven ability to optimise AI solutions for task completion, conversation quality, latency, retrieval effectiveness, cost, reliability, scalability, and user experience
• Proven ability to lead technical delivery, mentor engineers, review code, guide architectural decisions, and communicate effectively with stakeholders
• Willingness to remain hands-on in bot development, coding, integration, testing, debugging, and production support

Preferred Qualifications

Hands-on experience with Google GECX, including flows, intents, entities, routes, fulfilment, parameters, event handlers, environments, testing, and production deployment

Hands-on experience with Google Agent Development Kit (ADK) for developing, orchestrating, evaluating, or deploying AI agents

Experience integrating GECX or ADK solutions with Gemini models, enterprise APIs, webhook services, knowledge sources, and downstream systems

Experience implementing single-agent, multi-agent, supervisor, router, planner-executor, specialist-agent, or agent-to-agent patterns

Experience building enterprise voice bots or contact-centre solutions involving speech recognition, text-to-speech, interruption handling, escalation, and call transfer

Experience with Google Cloud services used to host, secure, integrate, monitor, and operate conversational AI workloads

Experience with Azure OpenAI, Azure AI Search, OpenAI APIs, Anthropic Claude, Gemini, open-source LLMs, or model-hosting platforms

Experience with vector search technologies such as Vertex AI Vector Search, Azure AI Search, Pinecone, Weaviate, FAISS, Milvus, Chroma, or Elasticsearch

Experience with LLM evaluation and monitoring tools such as LangSmith, PromptFlow, Ragas, DeepEval, TruLens, Arize Phoenix, or similar platforms

Experience creating golden conversation datasets, automated evaluation suites, red-team scenarios, and conversational analytics dashboards

Experience designing reusable bot frameworks, agent platforms, SDKs, tools, connectors, accelerators, or reference architectures

Experience integrating conversational agents with CRM, claims, contact-centre, document-management, knowledge-management, or workflow platforms

Experience with NLU, NLP, speech, multimodal AI, conversation analytics, security, privacy, and Responsible AI

At UnitedHealth Group, our mission is to help people live healthier lives and make the health system work better for everyone. We believe everyone-of every race, gender, sexuality, age, location and income-deserves the opportunity to live their healthiest life. Today, however, there are still far too many barriers to good health which are disproportionately experienced by people of color, historically marginalized groups and those with lower incomes. We are committed to mitigating our impact on the environment and enabling and delivering equitable care that addresses health disparities and improves health outcomes - an enterprise priority reflected in our mission.