About

Know about me

Data & AI Engineer

A versatile Data & AI Engineer with a jack-of-all-trades mindset, bringing hands-on expertise across data science, data engineering, and machine learning to build end-to-end intelligent systems. Experienced in designing Generative AI solutions, multi-agent architectures, and retrieval-augmented pipelines, while also delivering actionable insights through data analysis and predictive modeling. Comfortable working across the full AI lifecycle—from data processing and model fine-tuning to scalable backend development and cloud deployment—focused on building efficient, production-ready solutions and automating complex workflows in real-world environments.

// generative ai
LangChain LangGraph RAG Agentic AI Fine-tuning (LoRA) Prompt Engineering Embeddings
// machine learning & data
Python SQL Deep Learning NLP Predictive Modeling ChromaDB FAISS Snowflake
// platforms & deployment
Azure GCP Azure OpenAI FastAPI Streamlit Power BI MLOps

Resume

Check My Resume

Resume

Summary

Gaurav Patel

A versatile Data & AI Engineer with hands-on expertise across data science, data engineering, and machine learning to build end-to-end intelligent systems.

  • Pune, Maharashtra
  • +91 9173440539
  • patelgaurav454@gmail.com

Education

PG Diploma in Big Data Analytics (PG-DBDA)

Aug 2024 - Feb 2025

CDAC Kharghar, Navi Mumbai

BE in Computer Engineering

Aug 2020 - May 2024

Dr. D.Y. Patil College of Engineering and Innovation, Talegaon (SPPU Pune)

Certifications

Technical Skills

  • Programming: Python, SQL
  • AI & ML: Machine Learning, Deep Learning, NLP, LLMs, SLMs, Fine-tuning (LoRA), Predictive Modeling
  • Generative AI: LangChain, LangGraph, RAG, Embeddings, Prompt Engineering, Agentic AI
  • Data & Databases: ChromaDB, FAISS, Snowflake
  • Cloud & Tools: Azure, GCP, OpenAI, Azure OpenAI, Git, GitHub
  • Frameworks: FastAPI, Streamlit, Chainlit, REST APIs
  • Visualization & Others: Power BI, Data Analysis, RPA Integration

Professional Experience

AI Engineer

Feb 2026 - Present

Capgemini

  • Developed a full-stack AI-powered resume screening system achieving 80% accuracy and reducing screening time by 70% using semantic search and ranking algorithms.
  • Built a hybrid pipeline using TF-IDF, embeddings, and ChromaDB vector database enabling advanced natural language search and semantic matching against job descriptions.
  • Implemented a multi-page Streamlit interface for profile management, JD-based scoring, keyword search with re-ranking, and downloadable resume functionality; adopted internally by RMG team.
  • Developed a multi-agent RAG system (LangGraph) with 5-agent architecture, enabling query routing, context-aware response generation, and optimized chunking for high relevance retrieval.
  • Built a .NET project analyzer and upgrader agent used by 3 teams, improving upgrade efficiency by 30% through automated dependency resolution, security scanning, and API modernization workflows.
  • Developed AI-powered chatbot and ML forecasting solutions using Agentforce (Einstein AI), including real-time product retrieval, automated reminder systems, and customer-facing prediction interfaces.

Data Scientist

July 2025 - Jan 2026

Capgemini

  • Engineered custom training pipelines for fine-tuning SLMs, LLMs, and ML models on structured and unstructured datasets (text, JSON, XML) using LoRA and parameter-efficient techniques.
  • Optimized fine-tuning processes for resource-constrained environments (i5/AMD CPU, 16GB RAM, 8GB VRAM), enabling efficient, self-contained GenAI applications.
  • Architected a secure local model registry for deploying fine-tuned models as autonomous AI agents, achieving 100% offline on-prem inference.
  • Developed a custom Python framework following SOLID principles and OOP design to automate fine-tuning workflows, integrating data preprocessing, training, and evaluation pipelines, reducing manual effort by 90% and accelerating experimentation cycles.
  • Implemented robust MLOps practices including auto-versioning, tracking, and rollback mechanisms for model artifacts and LoRA adapters in resource-constrained environments.
  • Conducted a Proof-of-Concept (PoC) to validate model performance, documenting reproducible workflows and deployment using LM Studio.

Software Engineer

April 2025 - June 2025

Capgemini

  • Performed LCM trend analysis on 6-month historical data to identify underperforming projects across India, supporting data-driven decision making.
  • Developed interactive Power BI dashboards to visualize regional performance trends, highlighting significant variations and actionable insights.
  • Automated document workflows by developing Python scripts for modifying Word documents, improving operational efficiency.
  • Built a Python-based data extraction tool to retrieve structured information from PowerPoint files, enabling seamless integration with RPA workflows for a major travel technology client.

Freelance Data Engineering, AI/ML & Web Dev

Jan 2023 - March 2025

Independent Work

  • Delivered end-to-end software solutions across data engineering, AI/ML, automation, and web development for clients and independent projects over 2 years.
  • Raghuvanshi Rubber Industries: Developed responsive company website using HTML, CSS, JavaScript, Google Maps API.
  • Enterprise Data Pipeline: Developed scalable ETL pipeline using Python, dbt, Snowflake, Airflow, and Docker.
  • MailSweep Web App: Built Streamlit app automating Gmail cleanup via OAuth 2.0 & Airflow.
  • Sonar Rules Extractor: Concurrent Python script to extract SonarQube rules into JSON using async parsing.

Contact

Contact Me

My Address

Pune, Maharashtra

Social Profiles

Email

patelgaurav454@gmail.com

Contact No

+91 9173440539

Loading
Your message has been sent. Thank you!
Designed by Gaurav Patel