Headline

Senior Data Scientist | AI Researcher | Endurance Athlete | IIIT Hyderabad | Played Badminton Nationals once and now overusing that in titles.

About

Passionate about solving real-world problems at scale through AI, data, and innovation. Currently working as a Senior Data Scientist, bringing 5+ years of hands-on experience across Machine Learning, NLP, Data Engineering, and Product Development. I’ve had the unique opportunity to build and scale an AI healthcare startup as a co-founder and Tech Lead, turning an idea into a working product with real impact. I’ve also led and contributed to high-impact projects across industries, from crypto to healthcare, using data to drive decisions and build smart systems. 🏆 Highlights: • 1st place - Tianchi NLP Hackathon, Alibaba Group, China • 2nd place - IBM ML Competition, Tryst, IIT Delhi • Distinguished Author - Analytics Vidhya (Articles in Featured section) 🏃‍♂️ Beyond Work: I’m also an endurance athlete and marathoner, having represented India at the 2024 Berlin Marathon, and previously represented my state at the Badminton Nationals. Discipline, consistency, and resilience define how I show up, both in sport and in data. 🔍 What Drives Me: • Building robust AI systems that solve meaningful problems • Bridging data, tech, and business to create real-world impact • Mentoring, collaborating, and exploring wild ideas that just might work 💡 Let’s connect if you’re into building, solving, or running (literally).

Location

Hyderabad

AI stack

claude code

cursor

github copilot

hugging face

langchain

ollama

Work experience

Senior Data Scientist at BitGo, Jan 2024 - Present · 2 y 9 mo, Remote, BitGo is a leading institutional digital asset infrastructure company which acts as a major operational backbone for institutional crypto custody, trading, and wallets. ● Designed and deployed a production anomaly detection system for blockchain transactions, reducing anomalies by 90% and preventing ~$100K/month in estimated revenue leakage. ● Built chat-with-data, an agentic Slack chatbot on RAG infrastructure, giving clients, partners, and internal stakeholders self-serve data knowledge and insights on BitGo products inside Slack, reducing data support tickets by 50%. ● Architected and owned end-to-end, revenue-critical billing and analytics systems, turning high-volume, noisy blockchain transaction data into audit-ready financial outputs, cutting processing time by 90%. ● Led data strategy and execution for the Staking product (~30% of company revenue) through accurate reporting and billing. ● Architected data strategy for tax reporting, deploying Transformer-based models for document parsing and NER, optimizing inference throughput for 10,000+ enterprise documents. ● Owned data modeling, validation, and monitoring across financial reporting systems under strict correctness and compliance requirements.

Data Scientist at BitGo, Jul 2022 - Dec 2023 · 1 y 5 mo, Bengaluru

Co-Founder and CTO at Yushu Excellence Technologies Pvt. Ltd., Mar 2021 - Sep 2022 · 1 yr 7 mos, New Delhi, Delhi, India, Worked on building AI-powered voice solutions for healthcare. Incubated at BITS Pilani (PILANI INNOVATION AND ENTREPRENEURSHIP DEVELOPMENT SOCIETY) Our solution - voice assistant for doctors is built upon state of the art speech and natural language understanding models which provides incredibly fast and accurate voice experiences. It is aimed to reduce the documentation time by Doctors and in the long run, provides structured and well-maintained E-healthcare records.

Data Analyst at Coding Ninjas India, Jul 2020 - May 2022 · 1 yr 11 mos, Gurugram, Haryana, India, Coding Ninjas is one of the leading Indian Ed-tech companies, aiming to train the next generation of developers and transform the way tech education is delivered. ● Introduced a more Data-Driven Culture at Coding Ninjas by providing important Business Insights driven by data and strengthened the core of the team with Lean Analytics methodologies. ● Set up the analytical reporting for different b2b clients all over India. ● Hypothised and built a Lead Scoring Model by analyzing the pattern of tickets created by a user before and after order to build a model to predict order conversions. ● Student Learning Pattern recognition to predict users who miss deadlines and created actionable to stop that. ● Marketing Attribution to understand the impact of different marketing channels. ● Customer Segmentation and Colleges segmentation.

Data Science and NLP Intern at Optum, Jan 2020 - Jun 2020 · 6 mos, Mumbai Metropolitan Region, ● Worked on designing and building Clinical NLP engines to revamp medical coding workflows. ● Implemented and Improved Named Entity Recognition(NER) Algorithms to extract different medical facets from Medical Charts. ● Wrote production-grade highly maintainable code for multiple NLP and ML components. ● Worked on varied NLP projects ranging between Named Entity Recognition, Information Retrieval, Spell Correction, Semantic Search and Text/Document Classification. Tools and Frameworks used: ● Python (Pandas, spacy, Pytorch/ Tensorflow, scrapy) ● Git ● Elasticsearch ● Docker ● AWS EC2 ● Linux (Shell)

Education

Master of Science by Research, Computer Science, International Institute of Information Technology Hyderabad (IIITH)

Bachelor of Technology (B. Tech.), Computer Science And Engineering, BML Munjal University

Public links

github: https://github.com/dipansh-girdhar

medium: https://medium.com/@thepansh