Lead Agentic AI Engineer - Remote (LLM Orchestration)

Cognizant; Boise (ID); Remote; USD 100,000 - 130,000; Full time

Benefits offered by this job

Medical/Dental/Vision/Life Insurance

Paid holidays + Paid Time Off

401(k) plan

Long-term/Short-term Disability

Paid Parental Leave

Employee Stock Purchase Plan

Job summary

Cognizant seeks a Senior Agentic AI Engineer to lead a development team and design production AI agents for onshore and offshore client projects. The role is remote in the USA, with hands-on development, architecture, and collaboration with QA/UAT teams.

You will specialize in Conversational AI, Bedrock, Strands, and multi-agent orchestration, focusing on secure deployment, prompt engineering, and scalable agent workflows to deliver reliable generative AI solutions.

Qualifications

• Conversational AI & Agentic AI platforms required.
• Experience with AWS Lex or other deterministic bot.
• Proficient with Bedrock, Bedrock AgentCore and Strands.
• Voice and chat bot development experience.
• Agentic AI orchestration and integrations.
• LLM orchestration, tool integrations, and multi-agent workflows.
• Prompt engineering, grounding, and model evaluation.
• Secure AI deployment patterns and governance controls.

Responsibilities

• Lead Dev team across onshore and offshore.
• Hands-on development, design and architecture per client requirements.
• Support QA and UAT teams.

Skills

Conversational AI

Agentic AI

LLM concepts

Intent modeling

Prompt engineering

Tool calling

Agent workflows

RAG architectures

Tools

AWS Bedrock

Bedrock AgentCore

AWS Strands SDK

AWS Lambda

Amazon S3

DynamoDB

API Gateway

IAM

CloudWatch

GitHub Copilot

Job description

Cognizant seeks a Senior Agentic AI Engineer to lead a development team and design production AI agents for onshore and offshore client projects. The role is remote in the USA, with hands-on development, architecture, and collaboration with QA/UAT teams.

You will specialize in Conversational AI, Bedrock, Strands, and multi-agent orchestration, focusing on secure deployment, prompt engineering, and scalable agent workflows to deliver reliable generative AI solutions.