Looks like you have JavaScript disabled. For the full Twine experience, you will need to re-enable it.

Hello, I’m SANSKRUTI SANJAY DESHMUKH, a dynamic AI/ML Engineer with a Master’s in Data Science from the University of Minnesota and a B.Tech in Artificial Intelligence & Data Science. I specialize in building scalable ML models, NLP applications, and time-series forecasting using tools like BERT, TensorFlow, and Hugging Face. I have a proven track record in bioinformatics, predictive analytics, and ETL pipelines, with demonstrated impact across reproducibility, latency reduction, and robust evaluation metrics. In my ongoing work, I champion interdisciplinary AI applications, deploy modular ML pipelines with version control (Git) and containerization (Docker), and collaborate closely with researchers and engineers to translate complex data into actionable insights. I’m passionate about ethical AI, reproducibility, and delivering solutions that scale across teams and domains.…Hello, I’m SANSKRUTI SANJAY DESHMUKH, a dynamic AI/ML Engineer with a Master’s in Data Science from the University of Minnesota and a B.Tech in Artificial Intelligence & Data Science. I specialize in building scalable ML models, NLP applications, and time-series forecasting using tools like BERT, TensorFlow, and Hugging Face. I have a proven track record in bioinformatics, predictive analytics, and ETL pipelines, with demonstrated impact across reproducibility, latency reduction, and robust evaluation metrics. In my ongoing work, I champion interdisciplinary AI applications, deploy modular ML pipelines with version control (Git) and containerization (Docker), and collaborate closely with researchers and engineers to translate complex data into actionable insights. I’m passionate about ethical AI, reproducibility, and delivering solutions that scale across teams and domains.

SANSKRUTI SANJAY DESHMUKH

Data Scientist, AI Engineer, Full Stack Developer, +2





Hello, I’m SANSKRUTI SANJAY DESHMUKH, a dynamic AI/ML Engineer with a Master’s in Data Science from the University of Minnesota and a B.Tech in Artificial Intelligence & Data Science. I specialize in building scalable ML models, NLP applications, and time-series forecasting using tools like BERT, TensorFlow, and Hugging Face. I have a proven track record in bioinformatics, predictive analytics, and ETL pipelines, with demonstrated impact across reproducibility, latency reduction, and robust evaluation metrics. In my ongoing work, I champion interdisciplinary AI applications, deploy modular ML pipelines with version control (Git) and containerization (Docker), and collaborate closely with researchers and engineers to translate complex data into actionable insights. I’m passionate about ethical AI, reproducibility, and delivering solutions that scale across teams and domains.…Hello, I’m SANSKRUTI SANJAY DESHMUKH, a dynamic AI/ML Engineer with a Master’s in Data Science from the University of Minnesota and a B.Tech in Artificial Intelligence & Data Science. I specialize in building scalable ML models, NLP applications, and time-series forecasting using tools like BERT, TensorFlow, and Hugging Face. I have a proven track record in bioinformatics, predictive analytics, and ETL pipelines, with demonstrated impact across reproducibility, latency reduction, and robust evaluation metrics. In my ongoing work, I champion interdisciplinary AI applications, deploy modular ML pipelines with version control (Git) and containerization (Docker), and collaborate closely with researchers and engineers to translate complex data into actionable insights. I’m passionate about ethical AI, reproducibility, and delivering solutions that scale across teams and domains.

Available to hire

Hello, I’m SANSKRUTI SANJAY DESHMUKH, a dynamic AI/ML Engineer with a Master’s in Data Science from the University of Minnesota and a B.Tech in Artificial Intelligence & Data Science. I specialize in building scalable ML models, NLP applications, and time-series forecasting using tools like BERT, TensorFlow, and Hugging Face. I have a proven track record in bioinformatics, predictive analytics, and ETL pipelines, with demonstrated impact across reproducibility, latency reduction, and robust evaluation metrics.

In my ongoing work, I champion interdisciplinary AI applications, deploy modular ML pipelines with version control (Git) and containerization (Docker), and collaborate closely with researchers and engineers to translate complex data into actionable insights. I’m passionate about ethical AI, reproducibility, and delivering solutions that scale across teams and domains.

Skills

Experience Level

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Language

English

Fluent

Work Experience

Research Assistant at The Hauck Lab - University of Minnesota

July 1, 2025 - Present

Pioneered AI-driven RNA-seq data processing to identify differentially expressed genes, enabling publication in a tier-1 scientific journal and securing additional research funding. Orchestrated end-to-end RNA-seq workflows for 287+ samples, integrating ML-based pathway enrichment analysis to boost data reproducibility by 60% and investigate HDAC3 knockout impacts (GSE234232). Devised modular Python-based ML pipelines in JupyterLab/Anaconda, enhancing pipeline reusability by ~40% through automated feature extraction and model validation. Refined gene expression models with statistical ML methods, reducing computational overhead by 35% while maintaining high accuracy. Championed interdisciplinary AI applications, incorporating NLP for scientific literature mining to support hypothesis generation and model refinement. Deployed version-controlled ML experiments using Git and Docker, ensuring 100% traceability and facilitating seamless team collaboration on bioinformatics projects.

ML Engineer at Maxgen Technologies

June 1, 2025 - October 15, 2025

Engineered ETL pipelines in Apache Airflow and Python to handle ~690K daily transaction records, enabling anomaly detection models to operate in near real-time. Formulated Snowflake schemas (normalized + star) that supported ML-based risk scoring, improving dashboard responsiveness and cutting query latency by 50%. Automated compliance workflows with AWS Step Functions, Lambda, and S3, reducing reporting turnaround time by 38% through predictive ML integration. Integrated ML models as REST API services, ensuring smooth deployment of forecasting solutions and strengthening system scalability for client growth. Evaluated 60+ regression models in Scikit-learn, optimizing hyperparameters and delivering up to 85% accuracy on business KPI forecasting. Conducted EDA on 800K+ financial records, identifying data patterns that guided feature engineering and reduced model overfitting by 25%. Unified multi-source client datasets through SQL and Python pipelines, accelerating data readiness by 35%.