Agentic AI Platform Architect

Cognizant Technology Solutions•Charlotte, NC

57d

About The Position

Cognizant is one of the world's leading professional services companies, transforming clients' business, operating, and technology models for the digital era. Our unique industry-based, consultative approach helps clients envision, build, and run more innovative and efficient businesses. Headquartered in the U.S., Cognizant (a member of the NASDAQ-100 and one of Forbes World's Best Employers 2024) is consistently listed among the most admired companies in the world. Learn how Cognizant helps clients lead with digital at www.cognizant.com As an Agentic Architect, this role requires a unique blend of systems design, software architecture, AI/ML knowledge, and creative problem-solving.

Requirements

Hands-on AI Experience: Direct, hands-on experience building applications using LLM frameworks (e.g., LangChain, LlamaIndex) or agent frameworks (e.g., AutoGen, crewAI).
Data Engineering: Experience with data pipelines, message queues (Kafka)and data streaming technologies.
DevOps Mindset: Familiarity with CI/CD, infrastructure as code (Terraform, Pulumi), and observability (Prometheus, Grafana).
Passion for AI: A genuine enthusiasm for the future of autonomous agents and a desire to be a part of building it.

Responsibilities

System Design: Architect and design the end-to-end infrastructure for multi-agent AI systems, from data ingestion and processing to agent orchestration and action execution.
Agent Framework Development: Define the core components of an "agent," including their memory (short-term, long-term), planning capabilities (e.g., ReAct, RAG), and tool-use protocols.
Orchestration & Communication: Design the systems that allow agents to communicate, collaborate, delegate tasks, and work together to solve complex problems that are beyond the scope of a single agent.
Scalability & Performance: Ensure the architecture can scale to support thousands or millions of concurrent agents and complex workflows, maintaining high performance and reliability.
Safety & Governance: Implement robust frameworks for agent safety, ethical alignment, and governance. Design systems for monitoring, auditing, and "off-switching" agentic processes to ensure predictable and safe behavior.
Tooling & Integration: Design the APIs and integration points that allow agents to safely and effectively use external tools, databases, and third-party services.
Technical Leadership: Collaborate with ML engineers, data scientists, and backend developers to translate architectural vision into reality. Provide technical guidance and mentorship on best practices for building agentic systems.
R&D: Stay on the cutting edge of AI agent research (e.g., crewAI, LangGraph, AutoGen) and prototype new concepts to integrate into the core platform.