About the company
This position is listed on behalf of a partner company, who manages all applications and next steps. Our partner is looking for a Sr Generative AI Engineer (Agentic AI & RAG) based in India.
This is a hands-on engineering role focused on building production-grade generative AI systems for complex healthcare and patient-services use cases.
Responsibilities
- Design, develop, and productionize AI agents using Vertex AI Agent Builder, Claude APIs, Gemini Enterprise, and related enterprise AI technologies.
- Build AI-powered workflows for priority patient-services use cases, including intake automation, missing-information workflows, adverse-event detection, workload queue intelligence, QNCR automation, and chat-with-claims capabilities.
- Develop and maintain production-grade RAG pipelines, including vector stores, embeddings, retrieval strategies, and data-access workflows.
- Implement MCP server integrations and agent tools/function definitions that allow AI agents to interact safely with enterprise systems.
- Integrate AI capabilities into Salesforce Health Cloud, including Apex and LWC, as well as MuleSoft/DataWeave and Java-based SDLC environments.
- Create reusable prompt templates, agent architectures, implementation patterns, and engineering components that can be adopted across development teams.
- Contribute to a shared, quality-reviewed, version-controlled prompt and agent pattern library.
- Own the complete agent lifecycle, including development, deployment, testing, evaluation, monitoring, optimization, and retirement.
- Establish evaluation harnesses and quality standards to validate agent accuracy, reliability, safety, and performance before production deployment.
- Review AI-generated code produced by Salesforce, MuleSoft, and Java developers to ensure quality, maintainability, and compliance with engineering standards.
- Monitor production agents for accuracy, latency, cost, performance, and model or workflow drift, taking corrective action when required.
- Collaborate with technical leadership and distributed engineering teams to implement enterprise AI strategy and support a follow-the-sun delivery model.
- Deliver first-year priorities including an Intake Automation MVP and at least two additional AI workflow MVPs.
- Drive adoption of reusable agent patterns, prompt libraries, evaluation frameworks, and monitoring practices across the broader engineering organization.
Requirements
- 5+ years of professional software engineering experience with demonstrated success building and supporting production systems.
- Advanced Python development skills and working proficiency with JavaScript and/or TypeScript.
- Direct experience working with a cloud AI platform, with strong preference for hands-on experience with Vertex AI and its SDK.
- Demonstrated experience building LLM applications and applying prompt-engineering techniques with Claude, Gemini, OpenAI, or comparable foundation models.
- Practical experience designing and implementing RAG architectures, vector databases, embeddings, retrieval workflows, and associated evaluation approaches.
- Experience with agent orchestration frameworks such as CrewAI, LangChain, LangGraph, or Vertex AI Agent Builder.
- Experience integrating AI or software applications through REST and/or GraphQL APIs.
- Salesforce and/or MuleSoft integration experience is strongly valued, particularly with Apex, LWC, or DataWeave.
- Experience with MCP (Model Context Protocol) servers and agent tooling standards is a strong advantage.
- Background in healthcare or life-sciences technology, with awareness of regulated data environments and PHI/HIPAA considerations, is preferred.
- Experience with Salesforce development or Java development is an additional advantage.
- Familiarity with BigQuery, PostgreSQL, vector stores, or comparable data platforms.
- Strong understanding of the software development lifecycle and the ability to bring AI prototypes through production deployment.
- Strong problem-solving, communication, and collaboration skills, with the ability to work effectively alongside technical leads and distributed teams.
- Comfortable working within a follow-the-sun operating model and collaborating across time zones.
- A proactive, quality-focused mindset with an interest in building reusable systems rather than one-off AI experiments.
Conditions
- Opportunity to build production-grade generative AI and agentic AI solutions in a healthcare and life-sciences environment.
- Hands-on exposure to modern AI technologies including Vertex AI Agent Builder, Claude, Gemini Enterprise, LangChain, LangGraph, CrewAI, and MCP.
- Opportunity to work with enterprise platforms including GCP, BigQuery, PostgreSQL, Salesforce Health Cloud, MuleSoft, and Java.
- Ability to influence reusable AI engineering standards, prompt libraries, agent patterns, evaluation frameworks, and development practices.
- Opportunity to work on meaningful patient-services use cases with tangible operational impact.
- Collaboration with distributed engineering and AI teams in a global, follow-the-sun environment.