Job Summary
The Senior AI Engineer will join the AI Platform Team to build secure, scalable, and reusable enterprise AI capabilities that enable safe and efficient AI adoption across the organization. The role focuses on developing and deploying production-ready generative AI solutions, including retrieval-augmented generation (RAG)-based search, chat assistants, and AI agent services aligned with enterprise business domains. This hands-on engineering position emphasizes backend and platform development, infrastructure as code, APIs, cloud deployment, data storage, and operational readiness, with a strong focus on privacy, security, compliance, observability, and engineering standards.
Key Responsibilities
• Design, develop, and deploy secure, scalable, and reusable enterprise AI platform capabilities and domain-specific AI solutions.
• Build and maintain backend services, APIs, databases, and cloud-native applications that integrate AI capabilities into business workflows.
• Develop generative AI solutions, including RAG-based search, chatbots, copilots, and enterprise knowledge assistants.
• Implement and manage AWS-based solutions using services such as API Gateway, Lambda, Bedrock, S3, EventBridge, DynamoDB, PostgreSQL, CloudWatch, CDK, and Fargate.
• Use infrastructure as code (IaC), particularly AWS Cloud Development Kit (CDK), to provision and manage cloud resources.
• Apply prompt engineering techniques to improve grounding, reliability, usability, and output quality.
• Implement retrieval and generation workflows using embeddings, chunking, semantic retrieval, vector search, top-k, top-p, and related response-quality controls.
• Apply guardrails, safety controls, and output validation to mitigate risks such as hallucinations, prompt injection, jailbreak attempts, and unsafe content generation.
• Build, test, and deploy enterprise-grade APIs and services that integrate AI capabilities into existing business systems and workflows.
• Develop reusable platform components, prompt templates, service patterns, and other assets that support downstream engineering teams.
• Support the development and expansion of chatbot and AI agent solutions for benefits, claims, membership, groups, accumulations, health services, and provider networks.
• Evaluate, implement, and strengthen Model Context Protocol (MCP) and Agent-to-Agent (A2A) integration patterns.
• Apply software engineering best practices across testing, debugging, source control, continuous integration, and continuous deployment.
• Support cloud deployment, production operations, monitoring, troubleshooting, and ongoing improvement of AI services.
• Collaborate with product, engineering, quality assurance, architecture, security, and business stakeholders to deliver reliable, production-ready solutions.
• Ensure AI platform components and solutions align with enterprise privacy, security, compliance, observability, and engineering standards.
Required Qualifications
• 6-8 years of software engineering experience with strong hands-on experience in modern application development.
• Strong hands-on experience with Node.js and TypeScript as primary development technologies.
• Experience building backend and platform-oriented solutions, including APIs, services, databases, cloud deployment, and operational support.
• Strong hands-on AWS experience, including services such as API Gateway, Lambda, Amazon Bedrock, S3, EventBridge, DynamoDB, PostgreSQL, CloudWatch, AWS CDK, and Fargate.
• Hands-on experience with Amazon Bedrock.
• Experience with infrastructure as code (IaC), with hands-on AWS CDK experience required.
• At least 1 year of hands-on experience building generative AI solutions, preferably involving RAG, search-based AI, chatbots, copilots, or enterprise knowledge assistants.
• Practical understanding of prompt engineering and its impact on grounding, reliability, usability, and output quality.
• Working knowledge of embeddings, chunking, semantic retrieval, vector search, top-k, top-p, and related retrieval and generation concepts.
• Basic hands-on familiarity with AI guardrails, safety controls, and output validation, including awareness of hallucinations, prompt injection, jailbreak attempts, and content-safety risks.
• Experience building and deploying enterprise-grade APIs and services that integrate AI capabilities into business workflows.
• Strong software engineering fundamentals, including testing, debugging, source control, and CI/CD.
• Strong collaboration and communication skills, with the ability to work effectively across product, engineering, QA, architecture, security, and business teams.
Preferred Qualifications
• Experience with Python.
• Experience designing agentic AI solutions, orchestration frameworks, or tool-using AI workflows.
• Experience with Microsoft Azure in addition to AWS.
• Familiarity with AI evaluation, observability, tracing, benchmarking, or monitoring for generative AI solutions.
• Experience working in regulated environments such as healthcare, insurance, or financial services.
• Experience developing reusable platform components, internal SDKs, templates, or service catalogs for downstream teams.
• Experience with event-driven architecture, enterprise integrations, and cloud-native service patterns.
• Experience implementing or strengthening MCP and A2A integration patterns.
