AI Solutions Engineer (Generative AI & Agentic AI)

AI Solutions Engineer (Generative AI & Agentic AI)

Position Type: Full-time

Department: Digital & Technology

Job Family: Information Systems

About EVERSANA

EVERSANA is certified as a Great Place to Work across the globe. Our global team of more than 7,000 employees is committed to creating and delivering next-generation commercialization services to the life sciences industry. We serve more than 650 clients ranging from innovative biotech start-ups to established pharmaceutical companies. Our products, services and solutions help bring innovative therapies to market and support the patients who depend on them.

About the Role

The AI Solutions Engineer is the hands-on builder of the AI Hub Center of Excellence. This role turns architectural direction into working, production-grade agents and AI workflows that run on EVERSANA's enterprise AI stack (GCP, Vertex AI, Claude, Gemini Enterprise).

This engineer productionizes enterprise AI tooling for Patient Services use cases, builds reusable patterns other teams depend on, and integrates AI into the Salesforce, MuleSoft, and Java touchpoints of our SDLC. This 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

Minimum Qualifications

• 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

Our Cultural Beliefs

• Patient Minded: I act with the patient's best interest in mind
• Client Delight: I own every client experience and its impact on results
• Take Action: I am empowered and empower others to act now
• Grow Talent: I own my development and invest in the development of others
• Win Together: I passionately connect with anyone, anywhere, anytime to achieve results
• Communication Matters: I speak up to create transparent, thoughtful and timely dialogue
• Embrace Diversity: I create an environment of awareness and respect
• Always Innovate: I am bold and creative in everything I do

Equal Opportunity

EVERSANA is an Equal Opportunity Employer. From our inception, Diversity, Equity & Inclusion have always been key to our success. Our employees are people with different strengths, experiences, and backgrounds who share a passion for improving the lives of patients and leading innovation within the healthcare industry. Diversity includes race, gender identity, age, disability status, veteran status, sexual orientation, religion, and many other parts of one's identity. All of our employees' points of view are key to our success, and inclusion is everyone's responsibility.

Important Notice

EVERSANA would never require personal information or payment of any kind during the employment process. Please be aware of recent fraudulent job offers in the market misrepresenting EVERSANA. Recruitment fraud is a sophisticated scam commonly perpetrated through online services using fake websites, unsolicited emails, or text messages claiming to be a legitimate company.