Aug 2017 – Mar 2022 · 4 yrs 7 mos · Bengaluru, Karnataka, India

• I led a team of approximately 18 scientists, including both direct and skip-level reports, and was responsible for enhancing the customer experience in three large and complex product areas: Catalogue Quality, Shopping Experience, and Product Design Insights. Under my leadership, the team launched over 10 ML-driven products leveraging Natural Language Processing (NLP) and other Machine Learning (ML) techniques. These initiatives delivered significant business impact, including >$100M in incremental revenue growth, ~$10M in cost savings (estimated through controlled A/B experiments), and measurable improvements in critical business metrics such as catalogue health, instant answer rates on product pages, and a reduction in escalations from Amazon Business customers.
• This role required extensive cross-functional collaboration, and I partnered with science, product, engineering, design, and operations teams across the globe (including the USA, Australia, and Germany) to ensure worldwide impact. I guided my team to develop scalable ML solutions, drove global collaborations to productionise, test, and deploy these solutions, and devised hands-off-the-wheel strategies for their long-term sustainability.
• The team’s work was widely recognised, with 13 papers published in Amazon’s internal machine learning conference and 5 papers presented at external conferences. We also received 6 internal awards for projects that exemplified scientific innovation and Amazon’s "Bias for Action" principle.

Jan 2015 – Jul 2017 · 2 yrs 6 mos · Bangalore

• I am a Principal Research Scientist at Snapdeal and also serve as the Head of Research at Multimedia Research Group at Snapdeal, which I co-founded. Multimedia Research Group at Snapdeal is a group of immensely talented and hardworking researchers and engineers. The primary mandate of the team is to find Machine Learning solutions to seemingly hard challenges that Snapdeal faces as part of its business and operations.
• 1) New listings validation and standardisation: Amongst its many wins, the biggest one for MRG probably is the complete automation of new listings process. Validating and standardising new listings has been a pain point for e-commerce companies, particularly the ones that function as a marketplace. Most companies have to rely on human labor for this task that is not only costly but also time consuming and difficult to scale. Given its prowess in Machine Learning and Deep Learning (to be more specific), MRG has developed a state-of-the-art system that does completely automatic validation and standardisation of new listings (both text and image). The system is not only cutting edge in terms of ML algorithms and DL networks it uses for the task but also an engineering marvel for being able to achieve massive throughput without using too much hardware.
• 2) Image-based product search: Or more popularly known as Snap-n-Search is a new and intuitive experience for fashion shopping. As part of this project, we advanced the science behind the algorithms that powered Fashiate, in addition to making them work at scale. Unlike other companies, entire research and developement was done in-house by MRG.
• In addition, our team has worked on problems ranging from Ads recommendation to Fashion discovery, to matching products across competition, to search personalization etc.

Dec 2014 – Mar 2015 · 3 mos · Bangalore

• March'2015 - Snapdeal Acquires Fashiate.
• Fashiate is a new and intuitive experience for fashion shopping. Fashiate is for those times when you exactly know what you want, for those times when you have no idea what you want and for all times in between! You can be rest assured your fashiat-ing experience will be enjoyable and leave you uber-satisfied.
• When you are out and about and spot something you like, there is no way to find things that look ‘like that’. Well, not anymore! You can just take a picture and Fashiate will help you find things like that. Naturally, the picture of your favorite product can come from anywhere - movie posters, a magazine ad, a product catalog or anywhere else from the wide web!
• Want to find more pocket-friendly variants of out-of-budget products? Fashiate can find that too in no time. Not only that, you can refine your search based on patterns, colors and styles.

Dec 2011 – Dec 2014 · 3 yrs · Bangaon Area, India

• Working at Yahoo Labs Bangalore as a Research Scientist involved operating on large scale datasets with millions of images / terabytes of data, which I efficiently managed and processed using the Hadoop clusters and map-reduce framework. The work at Yahoo involved a mix of solo and team projects, where for some projects I lead teams of 2-5 researchers. My work also involved collaborating with different research and product teams across the globe.

Jul 2009 – Sep 2009 · 2 mos · Mountain View, California

Jul 2007 – Sep 2007 · 2 mos

Sep 2005 – Sep 2011 · 6 yrs

• Introduced new semantic image features with application to wide varieties of computer vision problems such as classification, annotation, retrieval etc. Also contributed significantly to the problem of searching across various media modalities. An expert at various generative modeling techniques of images, I analyzed the fundamental weakness in existing models and proposed a new model that surpassed any existing generative image model for classification.