SHUBHAM ANURAJ

Strong foundation in software development and machine learning with 3.5 years of experience. Currently seeking a challenging role as a Software Engineer, Machine Learning Engineer, Data Scientist or Data Engineer, with a strong experience in the general software industry.

Generalized Game Playing Agent
• A reinforcement learning (RL) agent with Monte Carlo Tree Search (Monte Carlo Simulation + UCB1) and deep learning. 90%-win rate with minimal CPU training.
AntiExcuseGPT
• LangChain project built with OpenAI LLM APIs to generate reasons and inspiration to do a particular thing someone might be procrastinating on. Uses FastAPI and Streamlit.
Live Facial Recognition
• Built an artificial neural network from scratch to classify family members who would be in front of the camera with 90% accuracy.
Multiple Level Sentiment Analysis
• A layered sentiment analysis NLP project using LSTM architecture. Full end-to-end pipeline created for classifying comments, with an accuracy of 80% on sentiments.
Character Level Language Model
• 0.5M parameter transformer-based language model from scratch trained on the book “David Copperfield” for generating text, given a prompt.
s-tronomic
• Personal website www.s-tronomic.in made from scratch with Flask backend. This contains blogs about topics from technology to philosophy, with over 10,000 aggregate views.
Fine-tuning model for Sentiment Analysis
• Using PEFT and LoRA for fine tuning a HuggingFace language model to complete sentiment classification for Yelp reviews. 88% accuracy after training.

• GitHub: https://github.com/sshanuraj
• LinkedIn: https://www.linkedin.com/in/shubhamanuraj/
• Portfolio: https://www.s-tronomic.in/about-us