プロフィール詳細

プロジェクトを作成

★★★★★

☆☆☆☆☆

★★★★★

☆☆☆☆☆

Dr. Karan S.に依頼

United States

AI/ML Business Strategy and Architecture Consultation | Biotech Founder

プロフィール概要

I have over 10 years of experience applying AI to solve high-impact problems across industry, startups, and research, backed by a PhD in Machine Learning from Georgia Tech. I help organizations design and implement AI strategies that move the needle on measurable business metrics. This includes the full AI lifecycle: from defining the right use cases and implementation strategies to deployment and continuous performance monitoring. At Google, I improved search relevance by integrating bespoke AI models directly into search engine architectures. During my time at Amazon, I enhanced product metadata categorization for e-commerce by combining similar model architectures with novel data collection strategies. Through my work in early-stage startups, I’ve built AI-driven platforms from concept to execution, translating advanced ML into tangible business outcomes. This work has also led to three patent applications, including one recently granted, reflecting a consistent focus on practical innovation. Part of my PhD involved working on biomedical data, where these interests led to a deep dive into the biotech space upon graduation. I recently co-founded a biotech startup that leverages AI to identify combinations of therapies that reverse the cellular age of immune cells, enabling more powerful cancer therapies and vaccine responses. Some of this work involves end-to-end data pipelines for next generation sequencing, with a focus on transcriptomic data, AI small molecule representations, gene networks + enrichment analysis.

専門分野

• ★ Machine Learning
• ☆ Data Analysis
• ☆ Image Processing
• ☆ Predictive Modeling & Analytics
• ☆ Data Processing
• ☆ Natural Language Processing
• ☆ Artificial Intelligence
• ☆ Deep Learning
• ☆ Computer Vision
• ☆ Information Retrieval
• ☆ Drug Discovery
• ☆ High Throughput Screening (HTS)
• ☆ High Content Screening/Imaging

サービス

• Writing
• Research
• Consulting
• Data & AI

Writing Technical Writing

Research Feasibility Study, Technology Scouting

Consulting Business Strategy Consulting, Scientific and Technical Consulting

Data & AI Predictive Modeling, Statistical Analysis, Image Processing, Algorithm Design-ML, Big Data Analytics, Text Mining & Analytics, Data Mining, Data Cleaning, Data Processing, Data Insights

職務経験

Co-Founder; CTO

Stealth Biotech

1月 2025 - 現在

Research Assistant

Georgia Institute of Technology

8月 2019 - 12月 2024

Student Researcher

Google DeepMind

8月 2022 - 1月 2023

Applied Scientist Intern

Amazon (United States)

5月 2022 - 8月 2022

Applied Scientist Intern

Amazon (United States)

5月 2021 - 11月 2021

Research Intern

IBM Research - Thomas J. Watson Research Center

6月 2020 - 8月 2020

Data Scientist

Astound AI

7月 2017 - 7月 2019

学歴

Ph.D. in Machine Learning (Interactive Computing)

Georgia Institute of Technology

8月 2019 - 12月 2024

B.S. in Computer Science; B.S. in Applied Statistics

Purdue University West Lafayette

8月 2014 - 8月 2017

認定資格

• MED001x: Drug Discovery & Medicinal Chemistry

  DavidsonX (EdX)

  https://courses.edx.org/certificates/b2da03553c994175ba75b1ef51c071af

  7月 2023 - 現在

出版物

PREPRINT

Samel, Karan, Sontakke, Nitish, Essa, Irfan(2025). Leveraging procedural knowledge and task hierarchies for efficient instructional video pre-training. arXiv preprint arXiv:2502.17352.

Samel, Karan, Beedu, Apoorva, Sontakke, Nitish, Essa, Irfan(2024). Exploring efficient foundational multi-modal models for video summarization. arXiv preprint arXiv:2410.07405.

Samel, Karan, Beedu, Apoorva, Haresamudram, Harish, Essa, Irfan(2024). On the efficacy of text-based input modalities for action anticipation. arXiv preprint arXiv:2401.12972.

Karan Samel, Zelin Zhao, Binghong Chen, Shuang Li, Dharmashankar Subramanian, Irfan Essa, Le Song(2022). Learning Temporal Rules from Noisy Timeseries Data . arXiv

Karan Samel, Zelin Zhao, Binghong Chen, Kuan Wang, Robin Luo, Le Song(2021). How to Design Sample and Computationally Efficient VQA Models . arXiv

CONFERENCE PAPER

Karan Samel, Cheng Li, Weize Kong, Tao Chen, Mingyang Zhang, Shaleen Gupta, Swaraj Khadanga, Wensong Xu, Xingyu Wang, Kashyap Kolipaka, et al. (2023). End-to-End Query Term Weighting .

Karan Samel, Monica Isgut, Neha Jain, Andrew Hornback, May Dongmei Wang (2023). GeneDAE: A Sparse Denoising Autoencoder for Deriving Interpretable Gene Embeddings .

Samel, Karan, Ma, Jun, Wang, Zhengyang, Zhao, Tong, Essa, Irfan(2023). Integrating Noisy Knowledge into Language Representations for E-Commerce Applications. 2023 IEEE International Conference on Big Data (BigData). Microsoft.AspNetCore.Mvc.Localization.LocalizedHtmlString 548--553.

Samel, Karan, Zhang, Houyu, Ma, Jun, Jiang, Haoming, Ping, Qing, Wang, Sheng, Xu, Yi, Zeng, Belinda, Chilimbi, Trishul(2023). SST: Semantic and Structural Transformers for Hierarchy-aware Language Models in E-commerce. 2023 IEEE International Conference on Big Data (BigData). Microsoft.AspNetCore.Mvc.Localization.LocalizedHtmlString 838--846.

Karan Samel, Zelin Zhao, Binghong Chen, Le Song (2021). ProTo: Program-Guided Transformer for Program-Guided Tasks . NeurIPS.

Karan Samel, Jiani Huang, Ziyang Li, Binghong Chen, Mayur Naik, Le Song, Xujie Si (2021). Scallop: From Probabilistic Deductive Databases to Scalable Differentiable Reasoning .

Karan Samel, Xu Miao (2018). Active Deep Learning to Tune Down the Noise in Labels . Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining.

JOURNAL ARTICLE

Karan Samel (2017). Predicting Advertisement Clicks Using Deep Networks: Interpreting Deep Learning Models . Journal of Purdue Undergraduate Research.