Srinath S

B.Tech AI & Data Science graduate (Anna University, CGPA: 8.0) with hands-on Generative AI, agentic workflow, and RAG pipeline experience across 4 production-grade projects and a published IEEE research paper. Built a production RAG pipeline (LangChain + FAISS) over 1,000+ GitHub source files with automated hallucination-reduction via RAG Triad validation; engineered an automated data scraping and normalization pipeline (BeautifulSoup + Requests + Pandas) processing 1,000+ unstructured records into structured datasets; and co-authored a peer-reviewed NLP paper at IEEE ICIRCA 2026 on intelligent ticket routing using SBERT embeddings and FAISS vector indexing over 4,500+ incident logs. Experienced in building LLM-powered agentic workflows, retrieval pipelines, data ingestion systems, and FastAPI-based backends.

Proficient in Python, LangChain, FAISS, LLMs, BeautifulSoup, Pandas, FastAPI, AWS, and Git — with a strong bias toward shipping production-ready AI systems.

Machine Learning Intern at Proitbridge (2025-11 – 2025-12)

Proitbridge — AI & Data Science Solutions Firm | Project-Based Technical Track

• Built and validated a credit risk classification pipeline on a 100+ feature consumer dataset, deploying preprocessing and model components on AWS EC2 for integration testing.
• Engineered a CatBoost credit risk classification model on a 100+ attribute consumer dataset, achieving 90% accuracy, ROC-AUC of 0.74, and optimal Log-Loss thresholds through feature transformation and hyperparameter tuning.
• Integrated Explainable AI using SHAP — generating global and local feature attribution plots to mathematically clarify model decision boundaries for business stakeholders.

B.Tech in Artificial Intelligence & Data Science – JCT College of Engineering & Technology, Anna University (2022 – 2026)