profile-pic

Gourav Jain

Software engineer with experience in backend development, machine learning, and web development. Currently at Evalueserve, specializing in Django-Rest-APIs for NLP-based products. Skilled in Python, Django, and various backend technologies, with a background in IoT and web development. Adept at optimizing performance, debugging issues, and collaborating with ML, frontend,
  • Role

    Machine Learning & IoT Engineer

  • Years of Experience

    2.10 years

Skillsets

  • Query Optimization
  • Matplotlib
  • MLFlow
  • Model evaluation
  • NumPy
  • OpenAI
  • OpenCV
  • pandas
  • Prompt Engineering
  • Machine Learning
  • rag
  • reranking
  • REST
  • Scikit-learn
  • spaCy
  • Tableau
  • Transformers
  • Python - 3.0 Years
  • LLMs
  • LangGraph
  • LangChain
  • Haystack
  • GPT-4
  • GenAI
  • Django
  • CI/CD
  • Azure DevOps
  • Swagger
  • Postman
  • MongoDB
  • Docker
  • Celery
  • NLP - 2.0 Years

Professional Summary

2.10Years
  • Feb, 2023 - Present3 yr 1 month

    Machine Learning Engineer

    Evalueserve
  • May, 2022 - Jun, 2022 1 month

    IoT Developer Intern

    IBM Phemesoft

Applications & Tools Known

  • icon-tool

    Python

  • icon-tool

    Swagger

  • icon-tool

    Docker

  • icon-tool

    Celery

  • icon-tool

    Postman

  • icon-tool

    Natural Language Processing

  • icon-tool

    pandas

  • icon-tool

    spaCy

  • icon-tool

    Data Preprocessing

  • icon-tool

    PHP

  • icon-tool

    HTML

  • icon-tool

    CSS

Work History

2.10Years

Machine Learning Engineer

Evalueserve
Feb, 2023 - Present3 yr 1 month
    Deployed enterprise GenAI/NLP solutions, including RAG chatbots and custom NER pipelines using Python, Django, Hugging Face, OpenAI API, and Weaviate. Improved GenAI retrieval and reranking, raising accuracy 30% and reducing latency on 2TB+ datasets. Added dynamic date filters and combined data to enhance chatbot responses. Collaborated with product/client teams to build scalable AI features. Mentored team members and led knowledge sharing on GenAI and ML technologies. Led model evaluations using precision, recall, F1-score for ongoing improvement. Ensured system stability via bug fixes, code reviews, and Agile practices. Managed ML workflows with MLflow and maintained data pipelines with MongoDB and Celery. Applied LangChain and LangGraph for modular and extensible LLM pipelines.

IoT Developer Intern

IBM Phemesoft
May, 2022 - Jun, 2022 1 month
    Created a Python/OpenCV smart doorbell with automated face detection for access control.

Major Projects

3Projects

Enterprise GenAI Chatbot with Advanced RAG Pipeline

    Built a GenAI chatbot leveraging open-source and commercial LLMs, integrating OpenAI, Hugging Face Transformers, and Haystack for business Q&A. Employed RAG pipelines with Weaviate vector database, handling over 2TB of data, and added filtration by date and source. Delivered Q&A with support for structured and unstructured data, incorporating custom prompt engineering, chunking, and metadata filtering.

Custom Named Entity Extraction (NER) Pipeline for Sensitive Medical Data

    Developed a custom NER pipeline using NLP techniques to extract sensitive medical entities, as well as other key entities such as names, organizations, and dates. Automated entity extraction from documents, enhancing efficiency and accuracy in handling complex datasets. Created and deployed secure APIs with Django Rest Framework to integrate the NER pipeline, ensuring smooth interaction and robust data protection.

LLM-Powered Wikipedia Q&A and Summarization (LangChain)

    Designed an interactive Wikipedia Q&A system using LangChain for LLM orchestration, integrating summarization features for improved user insight. Built scalable backend with modular prompts and retrieval, combining multiple data sources for robust knowledge extraction.

Education

  • Btech in Computer Science and Engineering (Specialization: IoT)

    University of Petroleum and Energy Studies (2023)