Sr AI Solutions Engineer (Generative AI & Agentic AI)

The AI Solutions Engineer is the hands-on builder of the AI Hub Center of Excellence. Where the AI Engineering & Enablement Lead sets architecture and governance, this role turns that direction into working, production-grade agents and AI workflows that ride on EVERSANAs enterprise AI stack (GCP, Vertex AI, Claude, Gemini Enterprise).

This engineer productionizes enterprise AI tooling for Patient Services use cases, builds the reusable patterns other teams depend on, and integrates AI into the Salesforce, MuleSoft, and Java touchpoints of our SDLC. It is a deep technical role for someone who wants to build real AI systems in a regulated healthcare environment, not just experiment.

ESSENTIAL DUTIES AND RESPONSIBILITIES:

Agent & Workflow Development

• Design and build AI agents on Vertex AI Agent Builder, the Claude API, and Gemini Enterprise.
• Productionize enterprise AI tooling for priority Patient Services use cases: intake automation, missing-information workflow, adverse-event detection, workload queue intelligence, QNCR automation, and chat-with-claims.
• Build and maintain RAG pipelines, vector stores, embeddings, and retrieval workflows against Patient Services data.
• Implement MCP server integrations and agent tool/function definitions that expose enterprise systems to agents safely.

Integration & SDLC

• Integrate AI capabilities into Salesforce Health Cloud (Apex, LWC), MuleSoft (DataWeave), and Java SDLC touchpoints.
• Build reusable prompt templates and agent patterns that the broader engineering team can adopt.
• Contribute to the shared prompt/pattern library with quality-reviewed, version-controlled components.

Lifecycle & Quality

• Own the agent lifecycle end to end: build, deploy, monitor, evaluate, and retire.
• Establish evaluation harnesses so agents are tested against defined quality bars before production.
• Review AI-generated code produced by Salesforce, MuleSoft, and Java developers, ensuring it meets ACTICS quality standards.
• Monitor deployed agents for drift, cost, latency, and accuracy; remediate as needed. Qualifications

MINIMUM KNOWLEDGE, SKILLS AND ABILITIES:

• 5+ years in software engineering, with hands-on experience building production systems.
• Advanced Python; competence in JavaScript/TypeScript.
• Direct experience with a cloud AI platform (Vertex AI strongly preferred) and its SDK.
• Demonstrated prompt engineering and LLM application development with Claude, Gemini, or equivalent models.
• Practical experience with RAG, vector databases, embeddings, and retrieval design.
• Familiarity with agent orchestration frameworks (CrewAI, LangChain, LangGraph, or Vertex Agent Builder).
• Experience integrating with REST/GraphQL APIs; Salesforce and/or MuleSoft integration experience a strong plus.
• Comfortable working on a follow-the-sun model with an onshore lead.

Preferred Qualifications

• Experience with MCP (Model Context Protocol) servers and agent tooling standards.
• Background in healthcare or life-sciences technology; awareness of PHI/HIPAA constraints.
• Salesforce (Apex/LWC) or Java development experience.
• Experience with BigQuery, PostgreSQL, or comparable data platforms.

Tools & Stack

• AI: Vertex AI Agent Builder, Claude API, Gemini Enterprise API.
• Orchestration: CrewAI, LangChain, LangGraph.
• Dev productivity: Claude Code, Cursor, GitHub Copilot.
• Data & cloud: GCP, BigQuery, PostgreSQL, vector stores.

First-Year Success Measures

• Intake Automation MVP and at least two additional AI workflow MVPs built and shipped to one or more programs.
• Reusable agent patterns and prompt library established and adopted by other engineers.
• Agent evaluation and monitoring practices operational for every production agent.
  
  Disclaimer: This job posting has been aggregated from external source. Role details, content, and availability are subject to change. Applicants are advised to confirm the latest information directly on the company website before applying.