About The Position
The AI Solutions Engineer is the hands-on builder of EVERSANA’s AI Hub Center of Excellence. Working from direction set by the AI Engineering & Enablement Lead, this role develops production-grade agents and AI workflows on the enterprise AI stack, including GCP, Vertex AI, Claude, and Gemini Enterprise. The engineer productionizes AI tooling for Patient Services, creates reusable patterns for other teams, and integrates AI into Salesforce, MuleSoft, and Java development workflows. This is a deeply technical role focused on building and operating AI systems in a regulated healthcare environment. The role owns the full agent lifecycle, from development and deployment through evaluation, monitoring, and retirement. It also establishes quality evaluation practices, reviews AI-generated code, and monitors production agents for drift, cost, latency, and accuracy.
Requirements
- At least 5 years of software engineering experience, including hands-on work building production systems.
- Advanced Python skills.
- Competence in JavaScript/TypeScript.
- Direct experience with a cloud AI platform and its SDK; Vertex AI is strongly preferred.
- Demonstrated prompt engineering and LLM application development experience with Claude, Gemini, or equivalent models.
- Practical experience with RAG, vector databases, embeddings, and retrieval design.
- Familiarity with agent orchestration frameworks such as CrewAI, LangChain, LangGraph, or Vertex Agent Builder.
- Experience integrating with REST or GraphQL APIs.
- Comfort working on a follow-the-sun model with an onshore lead.
Nice To Haves
- Experience with MCP (Model Context Protocol) servers and agent tooling standards.
- Healthcare or life-sciences technology background and awareness of PHI/HIPAA constraints.
- Salesforce (Apex/LWC) or Java development experience.
- Experience with BigQuery, PostgreSQL, or comparable data platforms.
- Salesforce and/or MuleSoft integration experience.
Responsibilities
- Design and build AI agents using Vertex AI Agent Builder, the Claude API, and Gemini Enterprise.
- Productionize AI tooling for Patient Services use cases, including intake automation, missing-information workflows, adverse-event detection, workload queue intelligence, QNCR automation, and chat-with-claims.
- Build and maintain RAG pipelines, vector stores, embeddings, and retrieval workflows using Patient Services data.
- Implement MCP server integrations and agent tool/function definitions that safely expose enterprise systems to agents.
- Integrate AI capabilities into Salesforce Health Cloud (Apex and LWC), MuleSoft (DataWeave), and Java SDLC touchpoints.
- Build reusable prompt templates and agent patterns for adoption by the broader engineering team.
- Contribute quality-reviewed, version-controlled components to the shared prompt and pattern library.
- Own the agent lifecycle, including building, deploying, monitoring, evaluating, and retiring agents.
- Establish evaluation harnesses to test agents against defined quality bars before production.
- Review AI-generated code produced by Salesforce, MuleSoft, and Java developers to ensure it meets ACTICS quality standards.
- Monitor deployed agents for drift, cost, latency, and accuracy, and remediate issues as needed.
- Build and ship an Intake Automation MVP and at least two additional AI workflow MVPs to one or more programs during the first year.
- Establish reusable agent patterns and a prompt library adopted by other engineers.
- Operationalize evaluation and monitoring practices for every production agent.
Stand Out From the Crowd
Upload your resume and get instant feedback on how well it matches this job.
What This Job Offers
Job Type
Full-time
Career Level
Mid Level
Education Level
No Education Listed
