AI & Generative AI Engineer specializing in LLM applications, RAG systems, NLP pipelines, and FastAPI backends for intelligent automation solutions.
I am an AI and Generative AI engineer with a strong foundation in statistics, machine learning, deep learning, and natural language processing. I specialize in building practical AI systems including LLM-powered applications, retrieval-augmented generation (RAG) pipelines, intelligent document processing, and API-based AI services.
I have hands-on experience developing end-to-end AI solutions such as resume parsing systems using large language models, embedding-based semantic search systems, OCR and structured data extraction pipelines, and chatbot backends using FastAPI and Flask. My work focuses on transforming unstructured data into usable intelligence through modern AI architectures.
I hold a Master’s degree in Statistics and have worked on multiple applied AI projects involving transformers, vector databases, prompt engineering, and cloud-based AI deployments. I enjoy solving real-world automation and data processing problems using efficient and scalable AI engineering practices.
I am available for freelance projects involving LLM application development, AI API integration, NLP pipelines, data extraction systems, and custom AI-backed web services.
Work Terms
Availability: 15–20 hours per week (evenings and weekends, IST timezone).
Preferred project types: LLM application development, RAG systems, NLP pipelines, document processing, AI-powered APIs, and backend integration.
Communication: Regular updates via chat or video calls as needed. Clear milestone-based delivery.
Payment terms: Fixed-price or hourly projects. Milestone payments preferred for larger projects.
Tools & stack: Python, FastAPI, Flask, LangChain, Transformers, Vector Databases, OCR pipelines, REST APIs, cloud deployment.
Time zone: IST (GMT +5:30).