Headline

AI Engineer | RAG Systems · NLP · Semantic Search · LLM Pipelines | Building Scalable, Production-Ready AI Solutions | Python · Flask · LangChain · Vector Databases

Location

Bengaluru

AI stack

antigravity

claude code

cursor

gemini

openai

perplexity

Work experience

AI Engineer at GTechnohubb Pvt. Ltd., Aug 2025 - Present · 11 mos, Bengaluru, Karnataka, India, Engineered a production-grade RAG system for intelligent document retrieval, reducing response latency through optimized chunking and efficient embedding strategies Built end-to-end document ingestion pipelines (text extraction, semantic chunking, embedding generation), improving context relevance for downstream queries Designed a modular AI architecture separating ingestion, retrieval, and inference layers, enhancing scalability and reducing maintenance overhead Developed and deployed semantic similarity models using SBERT and embedding-based retrieval for accurate real-time context fetching Integrated the RAG system with Flask REST APIs, enabling scalable real-time query processing and seamless third-party integration Fine-tuned NLP/ML models through structured hyperparameter optimization, improving performance across semantic applications Automated data preprocessing and validation workflows, reducing manual effort and increasing pipeline reliability Conducted error analysis and model monitoring to identify bottlenecks and maintain production-level system performance Applied LangChain and FAISS-based vector search to optimize retrieval pipelines in LLM-driven workflows

Education

Master of Computer Applications - MCA, Computer Science, Atria Institute of technology

Bachelor of Computer Application(BCA), Computer Programming, St. Aloysius Degree College, St. Aloysius PU Campus, Cox Town, Bangalore -05