Skip to content
View kjgpta's full-sized avatar

Highlights

  • Pro

Block or report kjgpta

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Please don't include any personal information such as legal names or email addresses. Maximum 100 characters, markdown supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
kjgpta/README.md

πŸ‘‹ Hey there, I'm Kshitij Gupta!

πŸš€ Machine Learning Engineer | πŸ€– LLMs & NLP Enthusiast | πŸ“š AI Researcher


πŸ† About Me

I'm a Machine Learning Engineer at Chubb Business Services India, specializing in LLMs, Databricks, and Azure Machine Learning.
I hold a Bachelor of Engineering in Electronics & Electrical Engineering from BITS Pilani, Pilani Campus.

πŸ’‘ My research focuses on Deep Learning, NLP, and Code-Switching NLP, and I’ve published work in ACL, AACL-IJCNLP, IALP, AISC and ACIIDS.

πŸ” I love exploring LLM reasoning, retrieval-augmented generation (RAG), and optimization techniques.


πŸš€ What I'm Working On

  • 🍳 Recipe API – Fine-tuning an LLM on recipe data to build an open-source culinary AI!
  • πŸ•΅οΈ WhoDunIt – A benchmark for evaluating deduction & reasoning in LLMs.
  • πŸ› οΈ Pushing the boundaries of efficient inference, distributed training, and NLP applications.

πŸ› οΈ My Tech Stack

πŸ“Œ Programming Languages

  • Python Java C C++ C# JavaScript

πŸ”₯ Machine Learning & Deep Learning

  • PyTorch TensorFlow Keras Hugging Face Transformers
  • DeepSpeed vLLM OpenAI API LangChain
  • Scikit-learn XGBoost LightGBM

πŸ—οΈ ML Infrastructure & MLOps

  • Azure Machine Learning Databricks Google Vertex AI AWS SageMaker
  • MLflow Kubeflow Ray Dask
  • Docker Kubernetes Terraform

πŸ›’οΈ Databases & Data Engineering

  • SQL NoSQL CosmosDB PostgreSQL MongoDB
  • Apache Spark Kafka Redis Elasticsearch
  • Databricks Delta Lake Snowflake

πŸ› οΈ DevOps & Tools

  • Git GitHub GitLab Jenkins
  • Linux Bash VS Code Jupyter Notebook PyCharm
  • Prometheus Grafana ELK Stack

πŸ–₯️ Web Development & APIs

  • Flask FastAPI Django
  • Spring Boot Node.js Express.js
  • GraphQL REST API gRPC

πŸ“œ Research Publications

πŸ“– WhoDunIt: Evaluation benchmark for culprit detection in mystery stories (ACL ARR, 2024)
πŸ“– Singaporean Conversational English-Malay Code-Switching Points (IALP, 2023)
πŸ“– Adapting Code-Switching Language Models with Statistical-Based Text Augmentation (ACIIDS, 2023)
πŸ“– MALM: Mixing Augmented Language Modeling for Zero-Shot Machine Translation (AACL-IJCNLP, 2022)
πŸ“– Data Augmentation for Automated Essay Scoring using Transformer Models (AISC, 2023)


🌐 Connect with Me

Let's connect and collaborate!

πŸ’Ό LinkedIn – @kjgpta
🐦 Twitter – @kjgpta
πŸ€– Hugging Face – WhoDunIt Benchmark
πŸŽ“ Google Scholar – Research Profile
🌐 Portfolio – Visit My Website
πŸ“§ Email – mailguptakshitij@gmail.com


πŸ’‘ "AI is the most powerful tool we haveβ€”let's use it wisely!" πŸš€

Thanks for stopping by! 😊

Pinned Loading

  1. kjgpta.github.io Public

    https://kjgpta.github.io/

    CSS 1

  2. NSC-Code-Switch-Analysis Public

    Code-switching analysis using linguistic techniques like part-of-speech

    Jupyter Notebook

  3. Code-Switch-Language-Modeling-for-English-and-Malay Public

    Code-Switched Data generation based on Part-of-speech and Language Modeling of the generated text.

    Jupyter Notebook 1

  4. Data-Augmentation-for-Automated-Essay-Scoring-using-Transformer-Models Public

    A novel data augmentation approach for Automated Essay Scoring and modeling it using Tranformers model

    Jupyter Notebook

  5. Unity-Projects Public

    In this Repository, you will find projects such as the roll-a-ball games in Unity 3D.

    C#

  6. Token-Bucket-Algorithm Public

    Token Bucket Algorithm with GUI interface

    Java