Headline

SDET | AI SDET | LLM Evaluation & GenAI Testing | DeepEval · Python · Agentic AI • Ragas |

About

AI SDET with 2+ years of experience building evaluation systems for LLMs, GenAI applications, and Agentic AI platforms. I build automated evaluation frameworks for Large Language Models using DeepEval, G-Eval, Python, and Pytest to validate: • Hallucination detection • Response faithfulness • Prompt quality • Agentic AI workflows • Multi-turn reasoning • Tool invocation accuracy At ExaThought, I designed end-to-end GenAI evaluation pipelines integrated with PostgreSQL and model APIs, reducing manual QA effort by 80%. I’ve worked on: • Clinical AI summary validation • Agentic AI testing • Prompt evaluation systems • AI regression pipelines • Enterprise analytics validation Tech Stack: Python, DeepEval, Pytest, FastAPI, PostgreSQL, Selenium, Docker, GitHub Actions Open to: AI QA Engineer | GenAI Testing | LLM Evaluation | AI SDET roles

Location

Bengaluru

AI stack

antigravity

claude code

claude

cursor

gemini

github copilot

Work experience

Software Engineer in Test at ExaThought, Dec 2023 - Present · 2 yrs 10 mos, Bengaluru, Software Engineer in Test — AI & GenAI Systems Exathought | Dec 2023 – Present | Bengaluru, Karnataka Built automated evaluation pipelines for Large Language Model and Generative AI systems across enterprise platforms. 🧠 GenAI Response Evaluation Platform Architected end-to-end evaluation pipelines using DeepEval and G-Eval to validate GenAI responses for quality, safety, and factual correctness. Designed custom evaluation metrics (hallucination detection, bias detection, clinical completeness) enabling data-driven model selection and prompt tuning. Integrated LLM evaluation pipelines with locally hosted model APIs and PostgreSQL databases for automated regression tracking. Reduced manual QA effort by 80%. Identified and documented 100+ defects across functional and performance layers, improving product stability before customer releases. 🏥 Clinical AI Summary Validation Led AI quality assurance for clinical summary generation system in healthcare analytics. Built automated DeepEval workflows to benchmark AI-generated medical summaries across accuracy, contextual alignment, and coverage dimensions. Designed 200+ validation test cases covering complex healthcare documentation and rare clinical events. Cut manual review time by ~60%. Ensured outputs met factual correctness and regulatory standards. 🤖 Agentic AI Testing & Enterprise Analytics Certified in Agentic AI Testing. Designed test scenarios validating agent planning, tool usage, and multi-turn memory retention. Built evaluation strategies to detect hallucinations and reasoning failures. Owned end-to-end testing strategy for enterprise AI analytics platform covering functional, regression, and edge-case scenarios. Validated model outputs against datasets to catch drift before production. Tech Stack: DeepEval, G-Eval, Python, Selenium, Pytest, FastAPI, PostgreSQL, GitHub Actions, Docker, BLE Testing

Data Analyst at Trainity, May 2023 - Sep 2023 · 5 mos, Bengaluru, Karnataka, India, • working on wide range of projects developed good skills such as SQL , MS Excel , Python , power BI • Importance of data cleaning , data analysis , data visualization . • Importance of normalizing and standardizing the data to support analysis . • good understanding of agile methodology

Education

Bachelor's degree, Electrical and Electronics Engineering, KLE Technological University - Hubballi (India)

Bachelor of Engineering, Electrical and Electronics Engineering, KLE Technological University