Senior AI Engineer

Senior AI Engineer (Contract) - Applied GenAI / Full Stack

High-Level Summary / Team Need
Looking for a Senior AI Engineer to join our AI Platform Team to help build secure, scalable, and reusable enterprise AI capabilities. This team enables safe, fast AI adoption across the enterprise by delivering governed platform capabilities, reusable patterns, and enterprise AI solutions such as RAG-based search, chat assistants, and agent/chatbot services aligned to enterprise business domains. This is a high-output, highly collaborative, hands-on engineering role focused on building and shipping production-ready AI solutions - not a research role and not a purely architectural role.
This role should skew toward backend/platform engineering, and the engineer needs to be able to operate across the full solution lifecycle - including infrastructure as code, APIs/services, cloud deployment, data storage, and production-ready delivery. Our team builds reusable AI platform components and domain-aligned AI solutions while working within guardrails related to privacy, security, compliance, observability, and engineering standards. We are not building frontend/UI applications on this team today; this role is centered on backend services, platform capabilities, and cloud-native delivery.


Required
• 6-8 years of software engineering experience with strong hands-on development experience in modern application engineering.
• Strong experience with Node.js / TypeScript; this is the non-negotiable primary language requirement for the role.
• Strong experience building backend/platform-oriented full-stack solutions, including APIs, services, databases, cloud deployment, and operational support.
• Strong AWS experience is required. Candidates should have hands-on experience with services such as API Gateway, Lambda, Bedrock, S3, EventBridge, DynamoDB, PostgreSQL, CloudWatch, CDK, and Fargate. Bedrock is required.
• Experience with infrastructure as code (IaC) is required, ideally with strong hands-on use of AWS CDK. CDK is explicitly required for this role.
• At least 1 year of hands-on experience building Generative AI solutions, ideally in RAG/search-based AI, chatbot/copilot experiences, or enterprise knowledge assistants. RAG/chatbot experience is sufficient for this hire
• Practical understanding of prompt engineering and how prompt design impacts grounding, reliability, usability, and output quality.
• Working knowledge of retrieval and generation concepts such as embeddings, chunking, semantic retrieval, vector search, top-k, top-p, and related controls that influence response behavior and quality.
• Basic hands-on familiarity with guardrails / safety controls / output validation, including awareness of risks like hallucinations, prompt injection, jailbreak attempts, and content-safety concerns.
• Experience building and shipping enterprise-grade APIs/services that connect AI capabilities into real business workflows.
• Strong software engineering fundamentals including testing, debugging, source control, and CI/CD.
• Strong collaboration and communication skills; we need a collaborative, high-output builder who works well with product, engineering, QA, architecture, security, and business stakeholders.


Nice to Have
• Python experience is preferred but not required.
• Experience with agent / agentic solution design, orchestration frameworks, or tool-using AI workflows is preferred, but not required for this first hire.
• Experience with Azure in addition to AWS.
• Experience with AI evaluation, observability, tracing, benchmarking, or monitoring for GenAI solutions. Basic familiarity is enough; deeper experience is a plus.
• Experience working in a regulated environment such as healthcare, insurance, or financial services.
• Experience contributing to reusable platform components, internal SDKs, templates, or service catalogs used by downstream teams.
• Experience with event-driven architecture, enterprise integrations, or cloud-native service patterns.


Examples of Work / Current Initiatives
This engineer would support work such as:
• Extending the benefits chatbot to support additional benefit systems.
• Standing up a claims chatbot / agent.
• Building a membership chatbot / agent.
• Building a group chatbot / agent.
• Building an accumulations chatbot / agent.
• Building a health services chatbot / agent.
• Building a provider network chatbot / agent.
• Proving out and hardening MCP / A2A patterns.
• Creating reusable base prompt templates and related reusable AI platform assets for downstream teams.