Shaleen Anand Taneja Lead Data Scientist

G

Lead Data Scientist

GALYTIX,

Jan 2024 - Apr 2024 (4 months)

Orchestrated and deployed a chat-based credit agent for a notable European bank using Mixtral 7B, Ray Serve, FastAPI, LanceDB for RAG, Hugging Face transformers, and Kubernetes. Developed advanced prompt engineering templates for user intent classification, content enrichment, and visualization generation. Recognized as Talent of the Month for March 2024.

Data Science Mentor

Great Learning

May 2023 - May 2024 (1 year 1 month)

Helped 50+ professionals transition into data science by mentoring the course taught by MIT faculty.

Senior Data Scientist

Zscaler

Jun 2022 - Jan 2024 (1 year 8 months)

Pioneered a component for detecting botnet traffic, improving anomaly detection precision from 4% to 50%. Engineered a robust testing framework for anomaly detection components, increasing testing coverage by 20%. Developed a kill chain detection framework using machine learning over honeypot logs, improving lead time by 20 days. Winner of team hackathon: Leveraged Azure Generative AI for mining IOCs from Cyber Security Blogs (GPT-3), resulting in a 5x increase in IOCs mined. US patent application in process for using ML over network logs (US20240119121A1).

P

Advisory Software Engineer (ML)

PITNEY BOWES INDIA,

Jul 2021 - Jun 2022 (1 year)

Implemented an NLP-based Customer Service Portal, reducing customer calls by 5% through advanced NLP techniques. Deployed a PySpark-based model on AWS Sagemaker, leveraging Dynamo DB as a feature store.

M

Solution Delivery Analyst

MCKINSEY KNOWLEDGE CENTER,

May 2020 - Jun 2021 (1 year 2 months)

Developed a data engineering workflow in a microservices architecture for a digital asset in the operations vertical. Built a digital asset from scratch using the Dash framework and Ag-Grid for a major American food manufacturer.

P

Senior Software Engineer

PITNEY BOWES INDIA,

Mar 2016 - May 2020 (4 years 3 months)

Managed and maintained Sagemaker Multi-Model real-time deployment, productizing models for 52 shipment facilities. Established Airflow as the central scheduling tool for data science activities, reducing processing time by 20%.

Shaleen Anand Taneja

About

Detail

Timeline

Résumé