AWS Agentic AI Engineer

Cognizant is seeking an AWS Agentic AI Engineer to design, build, and deploy autonomous and semi-autonomous AI agents on AWS. In this hybrid role based in Dallas, TX, you will focus on goal-driven, tool-using, multi-step systems that combine AWS AI/ML services with LLMs while integrating with enterprise environments and maintaining production-grade safety and reliability.

What you will do

• Design and develop agentic AI systems using Amazon Bedrock and other foundation models, including Claude and Titan.
• Build autonomous and semi-autonomous AI agents that support multi-step reasoning, planning, tool usage, action execution, and human-in-the-loop collaboration.
• Integrate with Amazon SageMaker for custom model training, fine-tuning, evaluation, and experimentation.
• Implement Retrieval Augmented Generation (RAG) solutions using Amazon OpenSearch, Amazon Aurora, DynamoDB, and vector databases such as FAISS or Pinecone.
• Optimize inference cost, latency, scalability, and reliability across AI workloads.
• Implement guardrails, validation layers, and human-in-the-loop controls to support safe, reliable, and predictable AI behavior.
• Mitigate hallucinations and address prompt injection risks, bias concerns, and model misuse scenarios.
• Ensure compliance with enterprise AI governance, security, and regulatory standards.
• Set up comprehensive logging, monitoring, observability, and audit trails for AI systems.
• Support production deployments, incident resolution, and root cause analysis for AI services.
• Continuously improve agent performance, reliability, robustness, and usability through iteration, monitoring, and feedback.
• Collaborate with architecture, DevOps, data engineering, security, and business teams to deliver end-to-end AI solutions.

Core requirements

• Bachelor’s degree in computer science, Engineering, Technology, or a related field.
• 3+ years of hands-on experience building agentic AI solutions using AWS cloud-native services (with 8–12 years overall IT experience).
• Strong expertise in core AWS services including AWS Lambda, Step Functions, EventBridge, S3, DynamoDB or Aurora, OpenSearch, Amazon Bedrock, and Amazon SageMaker.
• Advanced proficiency in Python for scalable AI systems and automation workflows.
• Proven ability to lead technical design and implementation of complex AI agent architectures and components.
• Hands-on experience with RAG solution design and applying model fine-tuning techniques.
• Demonstrated experience managing performance, scalability, reliability, and cost optimization for production AI workloads.
• Proven experience conducting code reviews, leading knowledge-sharing sessions, and making critical technology and architecture/framework decisions.
• Healthcare domain experience is desirable, along with knowledge of AI safety, governance, compliance, and responsible AI practices.
• AWS certifications such as Solutions Architect or Machine Learning Specialty are preferred; experience with LangChain and LangGraph is a plus.
• Excellent communication skills and the ability to collaborate effectively with technical and non-technical stakeholders.

Technologies you’ll work with

• AWS, Amazon Bedrock, Amazon SageMaker, Amazon OpenSearch, Amazon Aurora, DynamoDB, AWS Lambda, Step Functions, EventBridge, S3
• Python
• Claude, Titan
• FAISS, Pinecone
• LangChain, LangGraph