Senior Software Engineer II

Optum India; Bengaluru; On-site; INR 4,500,000 - 6,000,000; Full time

Benefits offered by this job

Restaurant

Job summary

Optum India is seeking a senior AI Platform Architect to design and deliver cloud-native AI solutions at scale. You will lead multi-team initiatives, shape platform strategy, and mentor engineers across global delivery teams.

You will own end-to-end architectural decisions including security, reliability, and cost efficiency. Responsibilities include building LLM-powered systems on Azure, implementing retrieval-augmented generation, agent-based frameworks, and reusable patterns.

Qualifications

• Bachelor's degree in Computer Science, Engineering, Information Systems, or related field.
• 8+ years software engineering experience with Agile/Lean development methodologies.
• 5+ years experience designing and delivering cloud-native solutions, preferably on Azure.
• Experience with JavaScript, TypeScript, React, SQL databases, Docker, Kubernetes, GitHub, and CI/CD pipelines.
• Experience architecting and delivering agent-based solutions utilizing frameworks such as Semantic Kernel, LangChain, AutoGen, LlamaIndex, or similar technologies.
• Experience designing multi-agent systems that leverage tool orchestration, function calling, reasoning, planning, and autonomous execution patterns.
• Experience with Azure AI technologies including Azure OpenAI, Azure AI Search, Cognitive Services, Functions, Cosmos DB, Service Bus, and related services.
• Proven experience leading technical initiatives and delivering large-scale enterprise applications.
• Deep experience designing scalable, secure enterprise architectures utilizing microservices, distributed systems, APIs, cloud platforms, and Infrastructure as Code.
• Demonstrated experience designing, developing, and deploying production AI applications utilizing LLMs, Generative AI services, AI Agents, or intelligent automation capabilities.
• Solid expertise with Python and modern API development practices.
• Deep understanding of prompt engineering, RAG architectures, vector databases, semantic search, embeddings, memory systems, and context-aware task execution.
• Demonstrated ability to mentor engineers, lead architecture discussions, conduct code reviews, and establish engineering standards.
• Demonstrated solid communication skills with the ability to influence technical and business stakeholders across global teams.

Responsibilities

• Architect, design, and deliver secure, scalable cloud-native applications and AI-powered solutions.
• Lead the design and implementation of production-grade AI applications utilizing LLMs, Generative AI services, AI agents, and intelligent automation capabilities.
• Architect and deliver multi-agent AI systems leveraging reasoning, planning, memory, tool orchestration, and autonomous execution patterns.
• Define and implement Retrieval-Augmented Generation (RAG) architectures using vector databases, embeddings, semantic search, and enterprise data sources.
• Lead the design of agent-based solutions using Semantic Kernel, LangChain, AutoGen, LlamaIndex, MCP, and related technologies.
• Establish reusable patterns for tool integration, function calling, orchestration, memory management, and agent interoperability across AI solutions.
• Design and optimize AI systems for production performance, scalability, reliability, latency, token utilization, throughput, and cost efficiency.
• Architect cloud-native AI platforms utilizing Azure OpenAI, Azure AI Search, Azure Functions, Cosmos DB, Service Bus, Cognitive Services, and related Azure technologies.
• Drive adoption of AI capabilities across business apps, reporting, workflow automation, and customer-facing experiences.
• Lead technical design discussions, architecture reviews, and implementation planning across multiple engineering teams.
• Define engineering standards, development practices, reusable frameworks, and reference architectures for AI-enabled development.
• Mentor engineers and provide technical leadership through code reviews and best practice adoption.
• Collaborate with product owners and stakeholders to identify opportunities where AI can accelerate business outcomes.

Skills

Azure Cloud

Python

LLMs

Prompt engineering

Agent-based

Semantic Kernel

LangChain

Microservices

IaC

Education

Bachelor’s degree

Tools

Semantic Kernel

LangChain

AutoGen

LlamaIndex

Azure Functions

Cosmos DB

Service Bus

Job description

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

• Architect, design, and deliver secure, scalable cloud-native applications and AI-powered solutions that align with business and enterprise technology objectives
• Lead the design and implementation of production-grade AI applications utilizing Large Language Models (LLMs), Generative AI services, AI agents, and intelligent automation capabilities
• Architect and deliver multi-agent AI systems that leverage reasoning, planning, memory, tool orchestration, and autonomous execution patterns
• Define and implement Retrieval-Augmented Generation (RAG) architectures utilizing vector databases, embeddings, semantic search, knowledge grounding, and enterprise data sources
• Lead the design of agent-based solutions utilizing frameworks such as Semantic Kernel, LangChain, AutoGen, LlamaIndex, MCP, and related technologies
• Establish reusable patterns for tool integration, function calling, orchestration, memory management, and agent interoperability across AI solutions
• Design and optimize AI systems for production performance, scalability, reliability, latency, token utilization, throughput, and cost efficiency
• Architect cloud-native AI platforms utilizing Azure OpenAI, Azure AI Search, Azure Functions, Cosmos DB, Service Bus, Cognitive Services, and related Azure technologies
• Drive the adoption of AI capabilities across business applications, reporting platforms, workflow automation solutions, and customer-facing experiences
• Lead technical design discussions, architecture reviews, and implementation planning across multiple engineering teams
• Define engineering standards, development practices, reusable frameworks, and reference architectures for AI-enabled application development
• Mentor engineers and provide technical leadership through code reviews, solution design guidance, architecture coaching, and best practice adoption
• Collaborate closely with product owners, business stakeholders, enterprise architects, and engineering leaders to identify opportunities where AI can accelerate business outcomes
• Partner with engineering teams to deliver end-to-end solutions spanning front-end applications, APIs, data platforms, AI services, and cloud infrastructure
• Drive adoption of Agile, DevOps, CI/CD, Infrastructure as Code, observability, and platform engineering best practices
• Evaluate emerging AI technologies, frameworks, and industry trends to influence AI platform strategy and long-term technology direction
• Champion Responsible AI, security, governance, compliance, and operational excellence within AI-enabled solutions
• Provide technical leadership for complex production issues, performance optimization efforts, and enterprise-scale application support
• 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 degree in Computer Science, Engineering, Information Systems, or related field
• 8+ years of software engineering experience with Agile/Lean development methodologies
• 5+ years of experience designing and delivering cloud-native solutions, preferably on Azure
• Experience with JavaScript, TypeScript, React, SQL databases, Docker, Kubernetes, GitHub, and CI/CD pipelines
• Experience architecting and delivering agent-based solutions utilizing frameworks such as Semantic Kernel, LangChain, AutoGen, LlamaIndex, or similar technologies
• Experience designing multi-agent systems that leverage tool orchestration, function calling, reasoning, planning, and autonomous execution patterns
• Experience with Azure AI technologies including Azure OpenAI, Azure AI Search, Cognitive Services, Functions, Cosmos DB, Service Bus, and related services
• Experience designing AI systems for production performance and economics, including model selection, latency, throughput, token/context utilization, caching, scalability, reliability, and cost optimization
• Proven experience leading technical initiatives and delivering large-scale enterprise applications
• Deep experience designing scalable, secure enterprise architectures utilizing microservices, distributed systems, APIs, cloud platforms, and Infrastructure as Code
• Demonstrated experience designing, developing, and deploying production AI applications utilizing LLMs, Generative AI services, AI Agents, or intelligent automation capabilities
• Solid expertise with Python and modern API development practices
• Deep understanding of prompt engineering, RAG architectures, vector databases, semantic search, embeddings, memory systems, and context-aware task execution
• Demonstrated ability to mentor engineers, lead architecture discussions, conduct code reviews, and establish engineering standards
• Demonstrated solid communication skills with the ability to influence technical and business stakeholders across global teams

Preferred Qualifications

• Azure AI Engineer, Azure Solutions Architect, or related certifications
• Experience defining AI platform strategy, reusable AI services, and enterprise AI architecture standards
• Experience with Model Context Protocol (MCP) or similar standards for reusable agent and tool integration
• Experience building enterprise AI copilots, agentic platforms, intelligent workflow automation, or AI-powered user experiences
• Experience implementing Responsible AI, AI governance, compliance, and security frameworks
• Experience with Azure AI Foundry and advanced Azure AI platform capabilities
• Experience in healthcare, analytics, reporting, or highly regulated industries
• Deep understanding of LLM integration, tool calling, prompt engineering, and context-aware task execution

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. #NIC