Papiha Joharapurkar

Data Scientist @Sanofi

Toronto, ON, CA
MOBILE NUMBERS
+91 *********19

Signup · Get unlimited contacts

WORK HISTORY

May 2024 — Present

Data Scientist @Sanofi

View department →

Toronto, ON, CA

Research & Development- Led technical workstream engineering scalable PySpark feature extraction pipelines on patient data to power Clinical Trial POS engine for simulating trial designs and cohort sizes for data-driven R&D investment decisions- Contributed to clinical trial enrollment forecasting leveraging TimesFM for zero-shot time-series inference, enabling precise timeline prediction and early identification of enrollment bottlenecks- Facilitated weekly stakeholder alignment between engineering and clinical research teams, ensuring data products addressed operational pain points and improved trial predictability.Real-World Data- Architected production-ready FastAPI backends with Pydantic and LangChain orchestration, integrating MongoDB vector stores to power enterprise GenAI RAG applications with React frontends serving 20K+ users- Built automated LLM evaluation pipelines using Ragas and LLM-as-a-judge frameworks, iterating on prompt engineering and retrieval strategies into leadership-approved, production-grade products.Commercial- Developed PyTorch-based patient churn prediction models incorporating causal inference and hypothesis-driven feature engineering; implemented A/B experimentation and statistical validation achieving strong field-rep adoption and enabling proactive retention strategies- Led algorithmic fairness and bias evaluation using statistical detection methods; engineered production monitoring dashboards for drift and bias tracking in Metaflow, and presented mitigation recommendations to the Patient Safety Board, shaping enterprise AI governance policies.Digital Strategy & Operations- Deployed Snowflake Cortex NLP services enabling natural language access to enterprise data for non-technical users, reducing time-to-insight- Engineered automated discovery pipelines within the Snowflake ecosystem using SQL and dbt-style transformations, streamlining raw data flow to real-time executive reporting and strategic dashboards.

EDUCATION

N/A

University of Toronto

Master of Biotechnology, Digital Health Technologies

N/A

International Baccalaureate

Turner Fenton S.S. OSSD, IB Diploma

N/A

McMaster University

Bachelor's of Health Sciences, Biology and Pharmacology Co-op

ABOUT PAPIHA JOHARAPURKAR

I always thought I\'d be a researcher in a lab coat pipetting samples and culturing cells. That obviously did not happen. I realized throughout my summer internships that even though I loved the scientific method, I was looking for a more dynamic way to apply it. The turning point came during my fourth-year thesis, where my predictive modelling results fundamentally changed how the field of gastroenterology approached pediatric intestinal failure. That\'s where I found my flow state - work that genuinely energizes me. That breakthrough (+ various degrees later) led me to Sanofi\'s AI Centre of Excellence, where I now work at the intersection of data science and strategic decision-making. In my day to day, you\'ll find me building production ML systems, engineering pipelines, and transforming complex datasets into products that deliver real impact. I thrive on ambiguous problems that require experimentation and hypothesis-driven thinking, and I\'m known for my agility in picking up new skills quickly to build thoughtful outputs. Outside of work, I\'m a builder at heart and I love sharing my philosophies on Substack/Tiktok. If you\'re tackling interesting problems in data science, product strategy, or building data-driven solutions in health, I\'d love to connect.

This profile is compiled from publicly available professional sources. Unifers is not affiliated with or endorsed by LinkedIn. Request removal of this profile.

Papiha Joharapurkar — Data Scientist at Sanofi in Toronto, ON, CA | Unifers