QA Engineer, Data Science

Design and perform end-to-end validation of machine learning models and Agentic GenAI solutions.,Validate Agentic GenAI solutions, including testing agent workflows, tool usage, orchestration logic, decision paths, and evaluating LLM outputs for accuracy, consistency, bias, hallucination risk, and alignment with business objectives.,Assess guardrails, prompt strategies, fallback mechanisms, and failure handling for GenAI.,Create statistical robustness and performance tests for trained models and GenAI systems, including simulated datasets that reflect real-world and edge-case scenarios.,Develop automated evaluation frameworks to measure model and agent quality, including precision, recall, stability, drift, response quality, and business KPIs.,Define and track data quality and model quality metrics, including input data validation, feature integrity, and output reliability.,Test and validate machine learning models and Agentic GenAI solutions using Python and related tools, analyze outputs and behaviors across scenarios, produce detailed validation reports, debug issues, and propose corrective actions to address methodological, data, or implementation gaps.,Collaborate with Data Scientists to deeply understand data pipelines, feature engineering, models, prompts, and agent architectures.,Work with Business SMEs to ensure models and GenAI agents meet stated objectives and risk tolerances.,Continuously seek better ways to test, validate, and monitor solutions through automation, new tools, and emerging technologies.

[object Object]

Bachelor's Degree