Agentic AI Engineer

Job Title- Agentic AI Engineer

Location- San Jose, CA

Salary Range- 70k to 80k

They will work with the AI Engineering and Platform teams to support the end-to-end development lifecycle for enterprise AI agents.

• Assist in building AI agent workflows that can orchestrate tasks across APIs, internal tools, knowledge sources, and approval processes.

• Support prompt engineering, tool/function calling patterns, retrieval design, guardrail implementation, and evaluation workflows.

• Contribute to backend service integration, agent telemetry, logging, monitoring, and continuous improvement of agent performance.

• Participate in testing for accuracy, security, reliability, hallucination mitigation, and production readiness.

• Document solution flows, reusable components, operating procedures, and learnings for team enablement.

Qualification and Specialization:

Bachelors or Masters degree in Computer Science, Information Technology, Data Science, AI/ML, Software Engineering, or a related engineering discipline.

Preferred foundational skills:

• Programming: Python, Java, JavaScript/TypeScript, or equivalent engineering language.

• AI/ML concepts: LLMs, embeddings, RAG, prompt design, model evaluation, and responsible AI basics.

• Cloud and integration basics: REST APIs, microservices, CI/CD awareness, Git, and secure development practices.

• Data handling: SQL/NoSQL fundamentals, JSON, document parsing, and knowledge-base preparation.

Unique Experience from this Role:

The role provides hands-on exposure to enterprise AI transformation by creating intelligent agents that move beyond simple chat experiences into governed, integrated, and measurable automation capabilities.

• Work on real-world agent use cases involving knowledge retrieval, workflow orchestration, validation, human-in-the-loop controls, and operational monitoring.

• Collaborate with experienced AI, platform, data, and delivery teams across distributed locations.

• Build practical understanding of how AI engineering is applied in BFSI environments where governance, security, auditability, and reliability are critical.

Learning outcomes for the Trainee:

By the end of the assignment, the trainee is expected to gain practical exposure in:

• Designing agent workflows using LLMs, tools, APIs, and enterprise knowledge sources.

• Implementing RAG patterns, prompt strategies, guardrails, and evaluation criteria for reliable agent behavior.

• Understanding secure integration, observability, operational support, and release-readiness for AI agents.

• Preparing reusable documentation, demos, and engineering artifacts that can support broader AI adoption across the team.