Job Description

Role Overview

Wipro Technologies invites applications for an experienced AI Architect to spearhead the design, development, and implementation of advanced multi-agent AI systems, with a particular emphasis on healthcare applications. This pivotal role demands expertise in building deep agent architectures and overseeing manager/supervisor agents, guiding cutting-edge AI solutions from initial conception through to robust, live enterprise deployments.

Key Responsibilities

• Architectural Leadership: Conceptualize and craft sophisticated agentic workflows leveraging modern frameworks such as LangGraph, AutoGen, Semantic Kernel, PydanticAI, and CrewAI. Ensure stateful orchestration, efficient supervisor routing, and fault-tolerant control flows that meet enterprise-grade reliability requirements.
• Multi-Agent System Design: Develop and coordinate multi-agent teams with distinct roles and collaborative methodologies—for example, researchers, planners, coders, and evaluators—ensuring seamless synchronous operation and goal alignment.
• Security and Interoperability: Integrate the Model Context Protocol (MCP) to facilitate secure, scalable plugin and tool interoperability, enhancing system extensibility and maintainability.
• Advanced Prompt Engineering: Employ innovative prompt engineering techniques to extract rules, parse complex content, and manage dynamic task execution across AI agents, optimizing performance and precision.
• Production Readiness and Compliance: Guarantee solutions are scalable, secure, observable, and optimized for cost-efficiency while adhering to enterprise standards and regulatory compliance frameworks.
• Stakeholder Collaboration: Engage proactively with global stakeholders to orchestrate the delivery of live AI deployments within cloud environments, ensuring alignment on objectives and technical directions.
• Continuous Improvement: Lead continuous refinement initiatives by rigorously evaluating AI frameworks, enhancing agent reliability, and implementing robust guardrails to ensure the safe and ethical operation of AI services.

Required Skills and Qualifications

• Minimum 7 years of professional experience in software engineering, including at least 2 years architecting large language model (LLM)-based or agentic systems.
• Hands-on proficiency with leading agent orchestration frameworks such as LangChain/LangGraph, AutoGen, Semantic Kernel, and CrewAI.
• Advanced Python programming skills, complemented by experience with cloud platforms—ideally Microsoft Azure—and container orchestration tools like Docker and Kubernetes.
• Demonstrated expertise in deploying multi-agent orchestration setups within production environments, as well as mastery of prompt engineering for rule and content extraction and familiarity with retrieval-augmented generation (RAG) workflows.

Mandatory Skills: Python for Data Science

Experience: 5-8 years