AI/ML Testing

Primary Skill : AI/ML, testing, Generative AI models inferencing using AWS Bedrock

Experience : 7 years

Current Status :Active

Job Duration : 3-6 Months

Job Description :

In this role, you will focus on the practical application and validation of Agentic AI, specifically engineering specialized Business Agents dedicated to tasks such as Auto-Cleansing, Risk Intelligence, Executive Summary generation, and Pricing Impact analysis. You must be versatile in modern AI, Gen AI, and Agentic AI paradigms, and be highly capable of operating within the AWS Bedrock ecosystem. A primary responsibility is the establishment of comprehensive evaluation, testing, and observability frameworks to measure LLM performance and agent reliability. You will rigorously test AI outputs, fine-tune models, and optimize agent workflows to meet stringent business requirements, ensuring that all deployed AI agents perform accurately and reliably in real-world business scenarios.