Aamod Khatiwada 

Data Scientist II
Microsoft, Silicon Valley Campus, Mountain View, CA, USA

Email: a$lastname$@microsoft.com

CV | Google Scholar | LinkedIn | Github Repo | Research Gate | Orcid

About me

I am Aamod Khatiwada, and I'm a Data Scientist II at Microsoft, Silicon Valley Campus, Mountain View, CA, USA. I am a part of the Microsoft Ads team, where I build LLM/SLM-powered retrieval, ranking, and relevance systems that serve Bing Search and Copilot Ads across global markets. My work also focuses on improving inference efficiency of language models. Before joining Microsoft, I graduated with a PhD in Computer Science from Northeastern University, Boston, under the supervision of University Distinguished Professor Renée J. Miller, where I also earned my master's degree. My PhD thesis, Table Discovery and Integration in Data Lakes, produced table discovery and integration methods such as SANTOS, ALITE, DIALITE, DUST, and TOPJoin, along with tabular foundation models such as TabSketchFM and widely-used open benchmarks including the SANTOS Benchmark (2K+ downloads). I did my undergraduate studies in Nepal (where I was born and raised).

During free times, I enjoy watching cricket and soccer, writing poems, stories, and news articles.

Some contents in this page are updated infrequently. Please visit my CV or Google Scholar profile for the most updated details.

Updates

2025 July 16 Our paper "TOPJoin: A Context-Aware Multi-Criteria Approach for Joinable Column Search", led by Harsha, got accepted for poster presentation at TaDA@VLDB 2025. Paper
2025 May 23 Our paper "Diverse Unionable Tuple Search: Novelty-Driven Discovery in Data Lakes" and short paper: "Fuzzy Integration of Data Lake Tables" got accepted at EDBT 2026. Thanks to my co-authors Roee and Renée.
2025 May 20 I presented our paper "TabSketchFM: Sketch-based Tabular Representation Learning for Data Discovery over Data Lakes", co-led by me and Harsha, at ICDE 2025. Paper
2025 March 14 I gave a guest lecture: "Session on Dataset Discovery in the era of Large Language Models" in DeepLearning.AI Lecture Series organized by BrainyCube Nepal.
2024 December 14 Our paper "TabSketchFM: Sketch-based Tabular Representation Learning for Data Discovery over Data Lakes", co-led by me and Harsha, and presented by Kavitha, won the best paper runner-up award at TRL@NeurIPS 2024. Video
2024 December 10 I have succesfully defended my PhD thesis on "Table Discovery and Integration in Data Lakes". I am grateful to my PhD advisor, PhD thesis committee, collaborators, friends, colleagues, and family. Thesis
2024 October 22 I presented our paper "A Generative Benchmark Creation Framework for Detecting Common Data Table Versions" at CIKM 2024. Kudos to my co-authors Daniel and Roee. Paper
2024 August 30 Our paper "ALT-GEN: Benchmarking Table Union Search using Large Language Models", led by Koyena, and co-authored by me, Roee and Renee, won the best paper award at Tada@VLDB 2024. Paper
2024 March 18 I gave a Guest Lecture at Boston University, USA on "Table Discovery and Integration in Data Lakes". Slides
2023 December 7 I passed my PhD Thesis Proposal Examination. Thanks to my advisor, PhD Thesis Committee Members and my collaborators.
2023 October 13 I accepted an internship offer from Microsoft for summer 2024. I will be interning at Redmond, Washington as PhD Data Scientist.
2023 August 29 I presented ALITE at VLDB 2023. Professor Renée J. Miller gave a keynote at TaDA Workshop@VLDB 2023 on "From Discovery to Integration of Data Lake Tables". The keynote covered ALITE and DIALITE papers.
2023 June 20 I, along with Grace presented SANTOS, and with Roee, demonstrated DIALITE at SIGMOD 2023. I also volunteered for the conference.
2023 May 22 I returned to IBM Research at Yorktown Heights as an AI Research Scientist for my summer internship.
2023 Apr 29 I received my Master's degree in Computer Science from Khoury College of Computer Sciences, Northeastern University.
2023 Apr 24 I received SIGMOD student Travel Award to attend SIGMOD Conference 2023. Thanks to the conference organization committee.
2023 Mar 10 Together with Grace, I gave a talk on "Table Discovery and Integration in Data Lakes: Challenges and Solutions" at Northeast Database Day, 2023. We also presented posters on SANTOS, STARMIE and ALITE.
2023 Feb 26 My demo entitled "Dialite: Discover, Align and Integrate Open Data Tables", co-authored with Roee and Renée has has been accepted for presentation at SIGMOD 2023.
2022 Dec 29 I visited Institute of Engineering, Thapathali Campus, Kathmandu, Nepal as a guest speaker and gave a talk on "Academic Research and Research Article Writing."
2022 Nov 15 My paper entitled "Integrating Data Lake Tables" has been accepted for presentation at PVLDB 2023.
2022 Nov 8 I achieved my PhD candidacy. Special thanks to my advisor, co-authors and colleagues.
2022 Oct 24 I presented my paper entitled "Knowledge Graph Embeddings for Causal Relation Prediction" at DL4KG@ISWC 2022. Oktie and Sola presented two other papers that I co-authored in the conference.
2022 Sept 5 This Fall, Professor Renée J. Miller is offering CS7290: Special Topics in Data Science course. I will be helping her as a Teaching Assistant for the class.
2022 Aug 26 I finished my summer internship at IBM Research, Yorktown Heights, NY. I will return back to IBM next summer (summer 2023) as an AI Research Scientist intern.
2022 Aug 16 SANTOS got accepted for SIGMOD 2023.

Experience

  • Research Interests

    • Large Language Models (LLMs / SLMs) and inference optimization
    • Retrieval, Ranking, and Recommendation Systems
    • Ads Relevance and Search
    • Data Discovery and Integration
    • Tabular Representation Learning / Tabular Foundation Models
    • Knowledge Graphs and Semantic Web
    • Data Management

  • Professional & Research Experience

    Feb. 2025 – Present Data Scientist II at Microsoft AI, Silicon Valley Campus, Mountain View, CA, USA (Microsoft Ads — Copilot Ads Relevance & Retrieval)

    • Lead design, training, evaluation, and production deployment of a transformer-based multilingual SLM ads relevance model for Microsoft Copilot; two-tower architecture with a distilled student tower for efficient serving. Delivered +15% offline AUC and ~10% online defect reduction with a revenue-neutral A/B outcome, validated across NA, LATAM, EMEA, APAC, and JP traffic groups covering tens of multilingual markets.
    • Delivered ~30% LLM/SLM inference efficiency gain via domain-knowledge-driven compression (US patent filed, 2026), enabling cost-effective serving of language models in ads retrieval and ranking.
    • Designed the LLM-as-a-Judge (model-assisted) evaluation framework used as the primary offline quality signal for Copilot Ads relevance model launches.
    • Authored a legacy-ranker deprecation framework adopted by multiple Bing Ads teams to safely modernize production ranking and retrieval components without revenue loss.
    • Mentor new team members on model training, data preparation, and LLM evaluation; drive cross-team technical direction with PMs, researchers, and engineers.

    Jun. 2024 – Aug. 2024 Data Science Intern at Microsoft Ads, Redmond, WA, USA

    • Trained optimized language models to understand online web search queries and recommend relevant ads.

    May 2023 – Aug. 2023 AI Research Scientist Intern at IBM Research, Yorktown Heights, NY, USA

    • Led TabSketchFM (tabular foundation model for data discovery) as first author, coordinating a 10-person cross-functional team of IBM researchers spanning modeling, systems, and evaluation; paper accepted at ICDE 2025 and awarded Best Paper Runner-up at TRL@NeurIPS 2024.
    • Developed the TOPJoin algorithm for joinable-table search, shipped as part of IBM watsonx.data.
    • Designed principled ways of creating benchmarks to fine-tune large language models for data discovery tasks.

    Sept. 2020 – Dec. 2024 Graduate Research Assistant at Data Lab, Northeastern University, Boston, MA, USA

    • Built semantic table union and integration systems (SANTOS, DIALITE) for large-scale data discovery over data lakes; multiple top-tier papers (PACMMOD, PVLDB) and best-paper awards.
    • Released the SANTOS Benchmark for table union search with 2K+ downloads, adopted by tens of follow-up research papers.
    • Designed principled LLM-driven benchmark generation frameworks for tabular tasks.

    May 2022 – Aug. 2022 Graduate Research Intern at IBM Research, Yorktown Heights, NY, USA

    • Led a project on detecting the causal relations in Knowledge graphs using embeddings and GNN-based models.

    Nov. 2018 – Jul. 2019 Smart Grow Nepal Private Limited, Bhaktapur, Nepal

    • Modeled “suction-based seed planting machine” and “Farm Monitoring Quadcopter”

    Apr. 2017 – Mar. 2018 Vortex Energy Solution, Lalitpur, Nepal

    • Supported the study of Renewable Energy scopes in Nepal

Publications

  • 2026

    • A. Khatiwada, R. Shraga and R.J. Miller, “Diverse Unionable Tuple Search”, EDBT 2026. Paper
    • A. Khatiwada, R. Shraga and R.J. Miller, “Fuzzy Integration of Data Lake Tables”, EDBT 2026 (short paper). Paper

    2025

    • A. Khatiwada, H. Kokel, I. Abdelaziz, S. Chaudhury, J. Dolby, O. Hassanzadeh, Z. Huang, T. Pedapati, H. Samulowitz, K. Srinivas, “TabSketchFM: Sketch-based Tabular Representation Learning for Data Discovery over Data Lakes”, ICDE 2025. Paper
    • H. Kokel, A. Khatiwada, T. Pedapati, H. Ananthakrishnan, O. Hassanzadeh, H. Samulowitz, K. Srinivas, “TOPJoin: A Context-Aware Multi-Criteria Approach for Joinable Column Search”, TaDA@VLDB 2025. Paper

    2024

    • A. Khatiwada, H. Kokel, I. Abdelaziz, S. Chaudhury, J. Dolby, O. Hassanzadeh, Z. Huang, T. Pedapati, H. Samulowitz, K. Srinivas, “TabSketchFM: Sketch-based Tabular Representation Learning for Data Discovery over Data Lakes”, TRL@NeurIPS 2024. (Best Paper Runner-up) Paper
    • D. C. Fox, A. Khatiwada and R. Shraga, “Generative Benchmark Creation Framework for Detecting Common Data Table Versions”, CIKM 2024. Paper
    • K. Pal, A. Khatiwada, R. Shraga and R.J. Miller, “ALT-GEN: Benchmarking Table Union Search using Large Language Models”, TaDA@VLDB 2024. (Best Paper Award) Paper

    2023

    • A. Khatiwada,R. Shraga and R.J. Miller , "DIALITE: Discover, Align and Integrate Open Data Tables" , in SIGMOD-companion, 2023. Paper
    • A. Khatiwada, G. Fan, R. Shraga, Z. Chen, W. Gatterbauer, R.J. Miller and M. Riedewald, "SANTOS: Relationship-based Semantic Table Union Search", in Proc. ACM Manag. Data (PACMMOD) 1, 1, Article 9 (May 2023). Paper
    • K. Pal, A. Khatiwada, R. Shraga and R.J. Miller, “Generative Benchmark Creation for Table Union Search”, 2023. Preprint
    • K. Srinivas, J. Dolby, I. Abdelaziz, O. Hassanzadeh, H. Kokel, A. Khatiwada, T. Pedapati, S. Chaudhury, H. Samulowitz, “LakeBench: Benchmarks for Data Discovery over Data Lakes”. 2023. Preprint

    2022

    • A. Khatiwada, R. Shraga, W. Gatterbauer and R.J. Miller, "Integrating Data lake Tables", in PVLDB, 16(4):932-945, 2022". Paper
    • O. Hassanzadeh, P. Awasthy, K. Barker, O. Bhardwaj, D. Bhattacharjya, M. Feblowitz, A. Khatiwada, L. Martie, S. F. Mbouadeu, J. Ni, A. Saha, S. Shirai, K. Srinivas and L. Yip, "Knowledge-Based News Event Analysis Toolkit", in ISWC, 2022. Paper
    • A. Khatiwada, S. Shirai, K. Srinivas and O. Hassanzadeh, "Knowledge Graph Embeddings for Causal Relation Prediction", in Deep Learning for Knowledge Graphs Workshop (DL4KG@ISWC), 2022. Paper
    • S. Shirai, A. Khatiwada, D. Bhattacharjya and O. Hassanzadeh, "Rule-Based Link Prediction over Event-Related Causal Knowledge in Wikidata", in 3rd Wikidata Workshop (Wikidata@ISWC), 2022. Paper

    2021

    • A. Sedai, G. Singh, R. Dhakal, A. Khatiwada, K. Khanal, B. Kumal, S.Gautam and A.K. Mishra, "Technical and economic feasibility of a fully solar-powered Airport in Nepal", in IEEE International Conference on Intelligent Systems, Smart and Green Technologies (ICISSGT), 2021". Paper

    2020

    • Sedai, A., Yadav, B.K., Kumal, B.B., Khatiwada, A. and Dhakal, R., "Performance analysis of Gravitational water vortex power plant using scale-down model", in Current Research in Hydropower Technologies, CRHT X, Kathmandu University, 2020". Paper

    2019

    • A. Khatiwada, P. Kadariya, S. Agrahari and R. Dhakal, "Big Data Analytics and Deep Learning Based Sentiment Analysis System for Sales Prediction", in IEEE Pune Section International Conference (PuneCon), Pune, India, 2019, pp. 1-6, doi: 10.1109/PuneCon46936.2019.9105719. Paper
    • A. Khatiwada, R. Dhakal and S. Shrestha, "Application of Maximum Power Point Tracking Algorithm for Determination of the Solar Electric Potential in Gorkha Bazzar, Nepal", in Springer International Conference on Recent Advances on Mechanical Infrastructure, Ahmedabad, 2019. Preprint

Patents

    • D. Saini, A. Khatiwada, Q. Lou and J. Jiao, “Domain Knowledge-Driven Compressions of LLMs”, 2026 (US patent filed).
    • A. Khatiwada, H. Kokel, G. Rossiello, U. Khurana, O. Hassanzadeh, D. Bhattacharjya, K. Srinivas, A.M. Gliozzo and H. Samulowitz, “Sensible Join Discovery Framework for Tabular Data Integration in Data Lakes”, 2025 (US patent filed).
    • O. Hassanzadeh, A. Khatiwada and S. Shirai, “Link Prediction Using an Ensemble of Representations and Rules”, 2025 (US patent filed).

Teaching Experience

  • Teaching Assistant

    • Fall 2022, CS7290, Special Topics in Data Science, Northeastern University, MA, USA
    • Summer 2020, CS2365-201, Object-Oriented Programming, Texas Tech University, TX, USA
    • Spring 2020, CS2350-001/002, Computer Organization and Assembly Language Programming, Texas Tech University, TX, USA
    • Spring 2020, CS2365-001/002, Object-Oriented Programming, Texas Tech University, TX, USA

  • Assistant Lecturer

    • Fall 2019, BEX Seniors, Filter Design, Tribhuvan University, Institute of Engineering, Thapathali Campus, Nepal
    • Fall 2019, BCA Freshmen, Digital Logic, Tribhuvan University, Institute of Engineering, Thapathali Campus, Nepal
    • Fall 2019, BCT/BEX Sophomores, Electronics Devices and Circuits, Tribhuvan University, Himalaya College of Engineering, Lalitpur, Nepal
    • Spring 2019, BAME Freshmen, Basic Electronics Engineering, Tribhuvan University, Institute of Engineering, Thapathali Campus, Kathmandu, Nepal
    • Spring 2019, BCT Juniors, Embedded System Design, Tribhuvan University, Himalaya College of Engineering, Lalitpur, Nepal
    • Spring 2019, BEX Freshmen, Basic Electronics Engineering, Tribhuvan University, Himalaya College of Engineering, Lalitpur, Nepal
    • Fall 2018, BCT/ BEX Sophomores, Electronics Devices and Circuits, Tribhuvan University, Himalaya College of Engineering, Lalitpur, Nepal
    • Fall 2018, BCE Freshmen, C Programming, Tribhuvan University, Himalaya College of Engineering, Lalitpur, Nepal

  • Trainer/ Instructor

    Apr. 2018 – Mar. 2019 4G Nepal Private Limited, Kupondole, Lalitpur, Nepal

Education

  • Graduate

    • Sep 2020 – Dec 2024, PhD in Computer Science, Northeastern University, USA (Advised by: Dr. Renée J. Miller). Thesis: Table Discovery and Integration in Data Lakes.
    • Sep 2020 – Apr 2023, Master’s in Computer Science, Northeastern University, USA.

  • Undergraduate

    • Nov 2018, B.E Electronics and Communication Engineering
    • Tribhuvan University, Institute of Engineering, Thapathali Campus, Kathmandu, Nepal
    • Division: Distinction
    • Rank: Department Topper

Awards and Achievements

    • Dec, 2024 Best Paper Runner-up Award at Tabular Representation Learning Workshop, NeurIPS 2024, for TabSketchFM.
    • Aug, 2024 Best Paper Award at TaDA@VLDB 2024 for ALT-GEN.
    • Sept, 2020 PhD Startup Fund from Khoury College of Computer Sciences, Northeastern University, MA, USA.
    • Apr, 2023 Received SIGMOD student Travel Award to attend SIGMOD Conference 2023.
    • Apr, 2020 Received Leadership And Mentorship Program (LAMP) Scholarship from the Dean of the Whitacre College of Engineering, Texas Tech University, TX, USA
    • 11 Dec, 2016 Awarded by Former Prime Minister of Nepal Dr. Baburam Bhattarai as the best Student in Department of Electronics and Communication Engineering, Tribhuvan University, Institute Of Engineering, Thapathali Campus, Kathmandu, Nepal
    • Awarded as the best student of the Electronics and Computer Department in 51st, 52nd, and 53rd Anniversary of Tribhuvan University, Institute Of Engineering, Thapathali Campus, Kathmandu, Nepal

Professional Service

Projects and Extra Curricular

  • Project Highlights

    • Developed IOT based Smart Fire Alarm and Security System during Internship at Research and Development Unit, First Aid Nepal, Kathmandu, Nepal
    • Developed Website and Online Examination Portal for 4G Nepal Private Limited, Lalitpur, Nepal
    • Designed Employee and Customer management system for SK Digital Institute, Morang, Nepal
    • Developed RFID based Business Intelligence enabled Hotel Management System for Attic Restaurant, Kathmandu, Nepal
    • Volunteered at Education Management and Information System (EMIS) Unit at Tribhuvan University, Institute of Engineering, Thapathali Campus on its projects: Campus Area Wi-fi Network Design and College Website Development and Management
    • Developed website for Galaxy Event Solutions, Washington, USA

    Jun 2020 - Present Core Team member at Brainycube Research, Kathmandu, Nepal

    Apr. 2020 – Present Technical Head at Career Counselling, Nepal

    • Monitor the IT wing of the organization.
    • Developed online entrance portal and examination discussion/ preparation blog.

    Selected News articles published in Nepal

    • सुन्दर तराईको अद्भुत वसन्तलाई नियाल्दा (onlinekhabar.com) Link
    • लाइसेन्स परीक्षामा ७२ प्रतिशत इन्जिनियर फेल- कहाँ भयो कमजोरी ? (nepalpress.com) Link
    • Ways To Upgrade Engineering Education (The Rising Nepal Daily) Link
    • कोरोना नियन्त्रणमा कहाँ चुक्यौँ हामी? (baahrakhari.com) Link
    • विश्वमा समाधान भएका केही उदाहरणीय सिमाना विवादहरु (Harekpal.com) Link

    Nov. 2017 – Dec. 2019 Secretary at Group of Innovation in Technology (GIT), Nepal

    • Engineering, Applied Science, Medical, and Business students/Alumni Organization
    • Carried out collaborative social works by using the technical knowledge from diverse fields

    Jun 2018 Key Speaker at Education Fair, Jhapa, Nepal

    • Addressed about 500 High School Graduates on the topic of “Prospect of Information Technology in Nepal”

    Oct 2017 Program Coordinator and Presenter at Tribhuvan University, Kathmandu, Nepal

    • Coordinated Welcome and Farewell Program organized by Students of the Electronics and Computer Department (attended by around 400 students, Department staffs, and faculties)

Last Updated on: September 10, 2026