Krishna Srujan Vaddiparthi
Teaching Assistant @ Rochester Institute of Technology
About
I’m a Data Scientist working at the intersection of engineering systems and machine learning, focusing on applying statistical and ML methods to complex real-world problems. My path into data science began during my undergraduate studies in mechanical engineering, where I worked on a robotics research project involving sensor integration and automation. While exploring ways to add a computer vision-based weed detection capability to the robot, I became deeply interested in machine learning and signal processing. That curiosity eventually led me to pursue graduate studies in Data Science at RIT. Before moving into applied machine learning systems, I worked as a Business Intelligence Analyst at Udaan, one of India’s largest B2B e-commerce platforms. There I built analytics pipelines and ran pricing experiments to support operational decision-making across stakeholder teams. That experience taught me how messy real-world data can be and how valuable well-designed analytics systems are. More recently, I spent a year as a Data Scientist Co-op at ITT Goulds Pumps working with the R&D hydraulic engineering group. My work focused on building machine learning models to support pump design evaluation under severe data constraints. I developed ensemble modeling pipelines using AdaBoost and Gradient Boosting, designed training workflows using stratified bootstrapping and leave-one-out cross-validation, and incorporated model uncertainty and interpretability to make predictions more reliable for engineering decisions. I also worked closely with domain experts to translate raw fluid mechanics variables into meaningful dimensionless features for model development. The resulting prediction tool was deployed within the R&D group and is now actively used by engineers. I also worked on vibration-based condition monitoring systems for industrial pumps, building ETL pipelines and classification models for fault detection using Bluetooth-enabled sensor data. Across these experiences, I’ve developed a strong interest in problems where machine learning must interact with complex real-world systems, imperfect data, and domain knowledge. I enjoy working closely with subject-matter experts to break down complicated processes and translate them into structured features, interpretable models, and practical decision-support tools. Outside of work, I’m curious about how data science intersects with geography, anthropology, and scientific exploration, and I’m interested in eventually working on problems that connect data with the physical and cultural world.
United States
Seneca Falls
Computer Software
Neo4j, NoSQL, Data Engineering, Geospatial Data, Extract, Transform, Load (ETL), MongoDB, FastAPI, Back-End Web Development, REST APIs, Generative AI, Generative Adversarial Networks (GANs), Cross-functional Coordination, Graphical User Interface (GUI), Tkinter, Supervised Learning, Online Tutoring, Optuna, Amazon QuickSight, Amazon S3, Statistical Analysis
Experience

Teaching Assistant
Rochester Institute of Technology, New York, United States
• Assisted Professor Tanweer Alam in GCIS 124 (Java) by providing support to students during class hours. • Conducted tutor and mentor hours to address student queries and enhance understanding of course material. • Graded assignments, quizzes, and class activities, ensuring timely feedback for student performance. • Collaborated with the professor to track and report student performance, contributing to academic success.

Teaching Assistant
Rochester, New York, United States
Assisted Professor Tanweer Alam with tutoring/mentoring and grading assignments of First year students for the GCIS-123 Software Development and Problem Solving in Python for the Fall 2025 semester.

Data Scientist
Seneca Falls, New York, United States
Hydraulic Engineering R&D - Led development of an uncertainty-aware ML decision-support system to screen hydraulic pump designs before committing to costly CFD simulation and lab testing, supporting high-stakes engineering decisions. - Replaced legacy heuristic models with a stability-driven ensemble architecture, improving predictive reliability (R-squared 0.33 → 0.68) while achieving balanced classification performance (precision/recall/F1 = 0.80) under severe data scarcity and class imbalance. - Designed modeling workflows prioritizing consistency, interpretability, and trust, including stability-aware hyperparameter tuning, stratified ensemble training, and calibrated uncertainty estimation over single-fit accuracy. - Integrated explainability and sensitivity analysis (feature attributions + domain-constrained what-if analysis) to help engineers understand why designs were predicted as stable or unstable and how feasible changes affect outcomes. - Productized the ML pipeline into a locally deployable desktop tool used by engineers and leadership during design reviews, reducing weeks-to-months of simulation-driven exploration to minutes-scale ML-guided screening. - Authored technical documentation, delivered live demos, and collaborated closely with domain experts to ensure adoption, usability, and alignment with engineering workflows.

Data Analyst
Seneca Falls, New York, United States
Motions & Control (i-ALERT) - Predictive Diagnostics - Developed a vibration data preprocessing pipeline for industrial pumps, transforming raw FFT sensor signals into harmonic-aligned RMS features to remove run-speed dependence and enable consistent modeling across operating conditions. - Conducted domain-driven exploratory analysis with vibration analysts to understand fault signatures (cavitation, imbalance, dry-run), reducing FFT dimensionality from thousands of points to interpretable frequency-band features and establishing a transparent baseline for fault classification.

Teaching Assistant
Rochester, New York, United States
- Assisting Professor Tanweer Alam in the course Software Development in Python. - Mentoring and supporting students in class, guiding them to develop problem-solving skills. - Helping them with troubleshooting during class and holding mentoring hours during the week. - Grading their quizzes, activities and assignments and providing constructive feedback.

Business Analyst
Bengaluru, Karnataka, India
- Designed and implemented a scalable ladder pricing framework across B2B product categories, increasing average order value and units per order by 70 percent while improving inventory utilization and logistics efficiency. - Automated the purchase-order approval workflow by introducing daily inventory run-rate visibility, reducing approval turnaround time by 80 percent and improving inventory transparency across national warehouses. - Built decision-support dashboards for ads and category teams to track ad performance, surface monetization opportunities, and improve visibility into revenue drivers across the marketplace. -Conducted buyer and field-team outreach to validate analytics insights, incorporating qualitative feedback into pricing and demand analysis.

Undergraduate Research Assistant
Hyderabad, Telangana, India
- Designed and built a CNC-based gantry robot for automated planting, irrigation, and weed removal, integrating multi-axis motion control with modular tool attachments. - Developed and calibrated embedded control logic using Arduino to coordinate motion, actuation, and tool sequencing within a constrained physical system. - Integrated environmental and process sensors (temperature, humidity, soil-nutrient sensing) for real-time monitoring and data logging to support closed-loop automation workflows. - Led project execution across mechanical design, electronics integration, and control software, coordinating a small engineering team and delivering a working prototype within academic timelines.
Krishna Srujan Vaddiparthi's Contact Information
Phone
Find the Right Leads
Find Verified Contact Data
What LeadContact does well
Find verified emails, phone numbers, and decision-makers with 98% accuracy.
Find Leads
Find the right people by company, role, industry, location, and more.
925M+ professional profiles

Find Emails
Access verified email addresses for your target contacts.
657M+ emails

Find Phone Numbers
Get cross-validated phone data from multiple top sources.
239M+ phone numbers

More Accurate. Lower Cost.
Find contact data in 1 tool with 98% accuracy
LeadContact integrates leading enrichment tools to deliver more accurate contact data—without paying for each one.
Great conversations start with the right contact.
It’s time to find yours.



