Shourjya Bhattacharjee profile photo 1 on Tal

Shourjya Bhattacharjee

Data Science @ GoKwik | Machine Learning | GenAI

Bengaluru

2+ years of work experience

GoKwik
Jul 20242 y 2 moPresent

Bengaluru, Karnataka, India

Checkout Product Recommendations/Personalization, Customer LTV Modeling, Ads Optimization
MSD
Jun 20236 mosNov 2023

Pune District, Maharashtra, India

Project: Price Simulation & Loss Forecasting • Built a web-based tool that simulates drug prices based on real-world economic scenarios and forecasts the potential impact of price fluctuations on product margins. This tool enabled scenario planning and directly supported strategic decision making, leading to a 5% ($200M) correction in the forthcoming marketing budget. • Received Merck INSPIRE recognition twice from senior colleagues for making significant and impactful contributions that drove the overall success of the project. Project: Marketing Mix Modeling & Promotion Investment Optimization • Developed Marketing Mix Models using panel data and advanced regression techniques (Pooled OLS/Ridge) for attribution of sales figures across various digital marketing channels. • Processed big data comprising up to 11 million rows and 7 thousand columns, leveraging AWS Glue and PySpark to enhance computational speed, efficiency, and scalability. • Developed GPU-accelerated code using JAX to implement a batch matrix multiplication based approach for data transformation, achieving a 96% reduction in code execution time from 25 minutes to 1 minute.
Indian Institute of Management, Indore
May 20232 mosJun 2023

• Implemented finite difference algorithms and conducted data-driven simulations using Python to model traffic flow. • Developed GPU-accelerated code using JAX to optimize convolution operations, reducing code execution time by 60%. • Automated code execution tasks and designed a modularized code structure, improving workflow efficiency and reusability.

Shourjya’s AI Stack

claude code
claude code
hugging face
hugging face
langchain
langchain
ollama
ollama
Qwen
Qwen
vLLM
vLLM

Education

Indian Institute of Technology, Madras

Dual Diploma, Programming and Data Science

Indian Institute of Technology, Madras

20214 yrs2025
Indian Institute of Technology, Indore

Master of Science - MS, Data Science and Management

Indian Institute of Technology, Indore

20222 yrs2024

Join Shourjya and 10k+ other professionals on

Tal Boss

Tal is the app where bosses meet engineers & builders directly, without middlemen

Download Tal Boss

Shourjya Bhattacharjee on Tal

Headline

Data Science @ GoKwik | Machine Learning | GenAI

About

Data Scientist with strong hands-on experience in Applied Machine Learning, Deep Learning, Mathematical Optimization, and Backend Engineering, recognized for creating impactful analytical models that support strategic decision-making. Proficient in Python (Polars, PySpark, XGBoost, PyTorch, JAX, FastAPI, vLLM), Java, SQL, and Docker. Skilled in Statistical Modeling, End-to-End ML System Development, and ML Model Deployment into Production (MLOps). Passionate about finding innovative, robust and scalable solutions to complex business problems using modern mathematical and statistical techniques.

Location

Bengaluru

AI stack

claude code

hugging face

langchain

ollama

Qwen

vLLM

Work experience

Applied Scientist at GoKwik, Jul 2024 - Present · 2 y 2 mo, Bengaluru, Karnataka, India, Checkout Product Recommendations/Personalization, Customer LTV Modeling, Ads Optimization

Data Scientist (Marketing Mix Modeling, Simulation, Optimization) at MSD, Jun 2023 - Nov 2023 · 6 mos, Pune District, Maharashtra, India, Project: Price Simulation & Loss Forecasting • Built a web-based tool that simulates drug prices based on real-world economic scenarios and forecasts the potential impact of price fluctuations on product margins. This tool enabled scenario planning and directly supported strategic decision making, leading to a 5% ($200M) correction in the forthcoming marketing budget. • Received Merck INSPIRE recognition twice from senior colleagues for making significant and impactful contributions that drove the overall success of the project. Project: Marketing Mix Modeling & Promotion Investment Optimization • Developed Marketing Mix Models using panel data and advanced regression techniques (Pooled OLS/Ridge) for attribution of sales figures across various digital marketing channels. • Processed big data comprising up to 11 million rows and 7 thousand columns, leveraging AWS Glue and PySpark to enhance computational speed, efficiency, and scalability. • Developed GPU-accelerated code using JAX to implement a batch matrix multiplication based approach for data transformation, achieving a 96% reduction in code execution time from 25 minutes to 1 minute.

Research Intern (Scientific Computing) at Indian Institute of Management, Indore, May 2023 - Jun 2023 · 2 mos, • Implemented finite difference algorithms and conducted data-driven simulations using Python to model traffic flow. • Developed GPU-accelerated code using JAX to optimize convolution operations, reducing code execution time by 60%. • Automated code execution tasks and designed a modularized code structure, improving workflow efficiency and reusability.

Education

Dual Diploma, Programming and Data Science, Indian Institute of Technology, Madras

Master of Science - MS, Data Science and Management, Indian Institute of Technology, Indore