Hello, I’m Shashank.

I’m a Senior Applied Scientist at Microsoft AI. I build machine learning systems that learn safely and effectively from human behavior.

View research Read my CV

About

A little about me.

I’m a Senior Applied Scientist at Microsoft AI, working on machine learning for ads. My research asks a practical question: how can intelligent systems learn safely and effectively from the people who use them?

I completed my PhD at the Information Retrieval Lab at the University of Amsterdam, supervised by Prof. Maarten de Rijke and Prof. Harrie Oosterhuis. My thesis focused on off-policy evaluation and learning for ranking and recommendation systems.

During my PhD, I worked with Meta AI’s Modern Recommender Systems teams in London and New York on two-stage recommendation and reinforcement learning for text-to-image diffusion models. Before that, I built search-ranking and query-understanding systems at Flipkart.

Experience

Industry & research

Education

Apr 2026—Now

Microsoft AI

Senior Applied Scientist
Ads · Bengaluru

Aug—Dec 2024

Meta AI · New York

Research Scientist Intern
RL for diffusion models

Aug—Dec 2023

Meta AI · London

Research Scientist Intern
Two-stage recommendation

Jul 2018—Jan 2021

Flipkart

Data Scientist
Search ranking & query understanding

Jan—May 2018

Conduent Labs (erstwhile Xerox Research)

Research Intern
Fake-news detection

May—Jul 2017

Tata Research Design and Development Center (TRDDC)

Research Intern
Adverse-drug reaction extraction

Apr 2021—Oct 2025

University of Amsterdam

PhD · Information Retrieval
Ranking & reinforcement learning

Jun 2015—Dec 2017

IIIT Hyderabad

MS by Research
Search & information extraction

Latest updates

Research, talks, and milestones

2026

[Jun] Our SIGIR 2026 paper on off-policy evaluation was featured in Microsoft Research’s newsletter.
[Apr] Joined Microsoft AI’s Ads team in Bengaluru as a Senior Applied Scientist.
[Apr] Our short paper analyzing β-IPS was accepted at SIGIR 2026.
[Mar] Our RL paper on diffusion fine-tuning from my Meta AI internship was accepted at TMLR.
[Feb] My dissertation abstract appeared in the December 2025 issue of SIGIR Forum.
[Jan] New analysis: β-IPS beats SNIPS in asymptotic mean squared error. Preprint.
[Jan] Gave a virtual talk at eBay, San Jose, on RL for recommendation and diffusion post-training. Slides.

2025

[Oct] Defended my PhD thesis on RL for ranking and generative models! Watch the defense.
[Aug] Invited to speak at LossFunk, Bengaluru, on RL for recommendation and diffusion models. Slides.
[Jun] Our two-stage counterfactual learning-to-rank paper from my Meta internship was accepted at ICTIR 2025.
[Mar] New preprint on RL for diffusion fine-tuning, from my Meta AI internship in New York.

Earlier updates 2017—2024

2024

[Oct] Gave a virtual talk at Expedia, London, on safe counterfactual learning to rank.
[Sep] Our papers on variational regularization and ranking policy optimization were accepted at CONSEQUENCES@RecSys 2024.
[Sep] The unbiased learning-to-rank tutorial recording is available, covering our WSDM, SIGIR, and FIRE tutorials.
[Aug] Joined Meta AI in New York as a Research Scientist Intern, working on RL for diffusion fine-tuning.
[Jul] Our baseline corrections paper was accepted at RecSys 2024 for an oral presentation.
[Jul] Our safety guarantees paper was accepted at CIKM 2024.
[May] Serving on the program committees for ICML, ICLR, SIGIR, RecSys, and ICTIR 2024.
[May] New preprint on optimal baseline corrections for off-policy contextual bandits.
[Mar] Slides from our WSDM tutorial on unbiased learning to rank are available here.
[Mar] Co-presenting our tutorial on unbiased learning to rank at WSDM 2024.

2023

[Oct] Our unbiased learning-to-rank tutorial was accepted at WSDM 2024 and FIRE 2023.
[Sep] Gave an invited talk at ShareChat on safe unbiased learning to rank. Slides · Video.
[Aug] Gave an invited talk at Meta AI, New York, on safe unbiased learning to rank.
[Jul] Joined Meta AI in London as a Research Scientist Intern, working on off-policy learning for two-stage recommendation.
[Jul] Two extended abstracts on safe ranking and preference-elicitation bias were accepted at CONSEQUENCES@RecSys 2023.
[Jun] Our paper on unbiased recommendation with deep generative models was accepted at ICTIR 2023.
[May] Our Flipkart work on user return-time prediction was accepted at CRUM@UMAP 2023.
[Apr] Our unbiased learning-to-rank tutorial was accepted at SIGIR 2023. I’ll lead the discussion.
[Apr] Our full paper on safe unbiased learning to rank was accepted at SIGIR 2023.
[Feb] Serving on the program committees for SIGIR and NeurIPS 2023.

2021–2022

[Aug 2022] Our VAE-IPS work was accepted for an oral presentation at CONSEQUENCES+REVEAL@RecSys 2022.
[Jun 2021—Jun 2022] Reviewed for ACL, EMNLP, ICLR, ICML, and NeurIPS.
[Sep—Nov 2021] Teaching assistant for Advanced Information Retrieval.
[May 2021] Reviewing for NeurIPS, EMNLP, and ICLR 2021.
[Apr 2021] Joined IRLab at the University of Amsterdam as a PhD student.

Pre-PhD

[Jul 2020] Serving on the program committee for EACL 2020.
[Apr 2020] Our position paper was accepted at ECNLP@ACL 2020.
[Apr 2020] Our paper was accepted at SIGIR 2020.
[Apr 2020] Serving on the EMNLP and AACL-IJCNLP 2020 program committees.
[Dec 2019] Serving on the program committee for WSDM 2020’s State-based User Modelling workshop.
[Nov 2019] Unable to review for ICML 2020 due to ill health (March 2020 update).
[Jul 2019] Serving on the program committee for ECIR 2020.
[Jun 2019] Reviewing for IRJ’s special issue on learning from user interaction.
[Mar 2019] Gave an invited talk on information retrieval from social media at BITS Pilani’s Alumni Research Talks. Slides.
[Oct 2018] Serving on the program committees for ECIR 2019 and ML4H@NeurIPS 2018.
[Jul 2018] Joined Flipkart’s Search team as a Data Scientist.
[Jun 2018] Our Conduent Labs internship paper on fake-news detection was accepted at ASONAM 2018.
[Jun 2018] Our TRDDC internship work was published in BMC Bioinformatics.
[Jun 2018] Serving on the program committees for ICON 2018 and DTMBio@CIKM 2018.
[Jan 2018] Joined Conduent Labs (formerly Xerox Research) in Bengaluru as a Research Intern with Manjira Sinha and Sandya Mannarswamy.
[Dec 2017] Two papers accepted at ECIR 2018.
[Nov 2017] Two papers accepted at NeurIPS 2017’s Machine Learning for Health workshop.
[Nov 2017] Gave invited talks on recommender systems at TCE and adverse drug reaction extraction at Duke-NUS, Singapore.
[Sep 2017] Two papers on news recommendation accepted at SeRECSys@ICDM 2017.
[Aug 2017] Our paper on semi-supervised adverse drug mention extraction was accepted at DTMBio@CIKM 2017.
[Jul 2017] Our paper on knowledge bases for text classification was accepted at KG4IR@SIGIR 2017.
[Jun 2017] Our neural-network paper on trust prediction was accepted at ASONAM 2017.
[May 2017] Our hate-speech detection work received media coverage in India. Read more.
[Apr 2017] Won the Best Poster Award at WWW 2017 for our work on hate-speech detection.
[Feb 2017] Poster paper accepted at WWW 2017.
[Feb 2017] Workshop paper accepted at WWW 2017.