SUYASH.

Data Scientist IV — Principal Platform Architect

• Enterprise Platform Adoption: Democratized causal data science by pioneering an enterprise-wide experimentation infrastructure across 4 distinct business units (In-Store, Pharmacy, Digital, and Private Brands); scaled cross-functional testing capacity from 3 to 8+ concurrent experiments/week, driving $150M+ in decentralized annual business decisions.
• Statistical Standardization: Operationalized an automated distributed Spark and CUPED variance reduction pipeline enterprise-wide to achieve a 35% error reduction; compressed experimental cycle times by 40% (from 28 to 12 days) for all cross-functional product and analytics teams.
• Data Democratization: Designed and deployed a custom GenAI Analyst Agent (SQL+RAG via LangChain and Gemini) over a 50TB+ enterprise dataset; empowered non-technical stakeholders to translate natural language queries into verified SQL, reducing post-experiment analysis latency from days to hours.
• Operational Velocity & Scaling: Built an Auto-Summary Agent in partnership with business leadership to autonomously capture experiment telemetry and benchmark results; unlocked 240–400 hours/week of collective organizational bandwidth by automating executive stakeholder reporting loops.
• Algorithmic Optimization: Redesigned the core assignment algorithm from the ground up to deliver 100% reliable, 30x faster randomization by minimizing Mahalanobis distance as the loss function.

Principal Engineer & Product Architect

Founded an applied AI research and development lab to proactively build and stress-test emerging technologies and extract proven architectures to de-risk enterprise deployments.

• ClinicOS (SaaS Deployment): Engineered an AI-powered healthcare management SaaS platform currently live in 8 clinics across rural India; conducted structured workflow mapping with physicians to implement real-time consultation transcription, automated prescription generation, and automated inventory pipelines.
• QuizBeef (RAG Production): Architected an AI-native document comprehension platform scaling to 700+ users; synthesized learning science literature to deploy LLM semantic parsing and FAISS-powered vector retrieval for adaptive multi-source question generation.
• mana-health (Agentic Systems): Developed an advanced multi-agent biometric orchestration platform implementing Critic-Reflexion loops; enabled autonomous agent self-correction and output verification across specialized physiotherapy and nutrition nodes.

Senior Data Science Analyst

• Overturned decade-old risk policy: Used XGBoost + Propensity Score Matching to prove employment verification had zero predictive value for high-FICO borrowers (R² < 0.01), then designed a surgical A/B test that unlocked $114M annualized volume and 300+ incremental customers/month through friction reduction.
• Enabled $1.8M in loan approvals: Identified and resolved critical iOS bugs through funnel analysis on the Automated Loan Approval platform, collaborating with engineering and UI/UX teams to restore conversion flow.
• Infrastructure Modernization: Migrated legacy SAS workflows to GCP BigQuery, reducing infrastructure costs by 12% and improving decision speed by 10+ hours/week.

Assistant Manager, Data Science

• Global Campaign Optimization: Orchestrated data-driven email personalization strategies for a 45M+ user base in Vodafone Germany; designed an advanced predictive logistic regression and A/B testing framework that expanded CTR by 28% (from 1.4% to 1.8%) and generated $11.2M in incremental revenue.
• Customer Lifetime Value Expansion: Developed complex linear regression models to predict multi-tier retention curves across varying subscription price points; strategically redirected marketing spend to optimize customer lifetime value (CLV) by 5%.

Data Science Engineering Intern

• Hybrid Predictive Modeling: Outperformed the existing production baseline by improving forecasting accuracy by 8.5% for Toyota vehicle sales; architected a hybrid time-series model combining Prophet and LSTM deep learning networks to isolate complex residual seasonality.
• Security Risk Mitigation: Mitigated authentication friction by constructing an automated anomaly detection pipeline on AWS SageMaker; engineered a dynamic risk-based thresholding system that slashed 2FA false positives by 13% without degrading user sign-up flows.

The University of Texas at Dallas

MS, Business Analytics • Jan 2021 – Jun 2022

Dean's Scholar; President, Data Science Club — led workshops and speaker series. Top Student Mentor for Data Science track: answered 800+ questions and coached 70+ students.

Pune University

BS, Computer Science and Engineering • Jun 2016

GenAI & Agentic Systems

LangChain, RAG (Retrieval-Augmented Generation), Context Engineering, LLMs, Prompt Engineering, Autonomous Agents, SQL+RAG, dbt, Snowflake

Causal Inference & Experimentation

Causal Inference, CUPED, Bayesian Methods (PyMC), Propensity Score Matching, Synthetic Controls, Heterogeneous Treatment Effects (HTE), Uplift Modeling, A/B Testing, SRM Detection

Data & Infrastructure

Python, SQL, PySpark, BigQuery, Airflow, Spark, GCP (Vertex AI), AWS (S3, SageMaker), Docker, Pandas, NumPy, Scikit-learn, TensorFlow

Visualization & Tools

Tableau, Streamlit, Git, Azure

Certifications

Google Analytics