top of page

Our Mission 

To bring Equity to AI by making it Simple, Accessible and Affordable

The right people make all the difference

At the heart of Berrijam AI, our founders are true pioneers in the field of artificial intelligence. Their relentless pursuit of innovation has resulted in 10 patents for groundbreaking AI technologies and 15 influential research papers. Their expertise and dedication have driven the development of AI solutions, trusted and used by millions of people every day. We are immensely proud of their achievements and their unwavering commitment to advancing the capabilities of AI.

Ruth Mierowsky, Co-Founder and Head of AI & Product at Berrijam

Ruth Mierowsky

Co-Founder
Head of AI &

Product

  • LinkedIn
Avi Misra, Founder and  CEO at Berrijam

Avishkar Misra

Founder

CEO

  • LinkedIn
Ashwin Srinivasan, Co-Founder and Head of Product Infrastructure at Berrijam

Ashwin Srinivasan

Co-Founder

Head of Product Infrastructure

  • LinkedIn
Ian Kemp, Co-Founder and Head of Business Strategy - USA at Berrijam

Ian Kemp

Co-Founder
Head of Business Strategy, USA

  • LinkedIn
Jag Misra, Co-Founder and  Head of Marketing and Community Outreach at Berrijam

Jag Misra

Co-Founder

Head of Marketing and Community Outreach

  • LinkedIn

Experience matters

Explore our team's achievements in areas such as product recommendations, ad targeting, IoT data synthesis, Natural Language Processing (NLP) and medical image analysis to see how we can transform your business with AI.

Amazon Go

AmazonGo is a re-imagining of what a retail shopping experience should look like. Avishkar and team invented new solutions and capabilities. Computer vision, sensors, hardware and artificially intelligent algorithms blend into the background to create a magical shopping experience with AmazonGo.

Patents:

  • US9996818B1 - Counting inventory items using image analysis and depth information

  • US10882692B1 - Item replacement assistance

  • US10169677B1 - Counting stacked inventory using image analysis

  • US10789483B1 - Image based inventory item counting

  • US10949801B1 - Inventory item release apparatus and method

  • US10671856B1 - Detecting item actions and inventory changes at an inventory location

Amazon_Go_in_Seattle,_December_2016.jpg

Product Recommendations

"Once in a decade leap", was what Jeff Wilke (CEO of Amazon's Consumer Division) had called the algorithm created by our founder and CEO Avishkar Misra at his re:MARS 2019 keynote. 

Avishkar invented a new formulation for product recommendation which was 2x better than Amazon's state of art in recommendation. 

  • Video - Jeff Wilkie's Talk at re:MARS 2019

  • Paper - The Effectiveness of Two-layer Neural Network for Recommendations

  • Article - The History of Amazon’s Recommendation Algorithm

 

Patent:

  • US10290040B1 - Discovering cross-category latent features

NLP-Powered Multilingual AI Features

Ruth, our co-founder built a multilingual knowledge-base recommendation system that utilized NLP techniques to provide real-time article and similar case suggestions. Additionally, Ruth and team developed a multilingual topic modeling feature to give customers a better understanding of their key feedback and problem areas. Furthermore, real-time language detection APIs were implemented for use in call-routing and sentiment analysis, enhancing the overall user experience and operational efficiency.

What-is-nlp.png

Medical Image Anlysis

High Resolution CT scans are a non-invasive way to help radiologists diagnose diseases. Yet going through 100s of images per patient can be time-consuming. LMIK project was looking at ways to automate the analysis of lung anatomy and diseases in scans, to help radiologists.

Papers:

lung_seg_eg.webp
process_net.webp

Incremental Engineering

Software engineering of vision systems is challenging when data trickles in and the algorithms need to evolve over time. Avishkar used incremental knowledge acquisition techniques to provide ways to deal with the changes rapidly and in doing so speed up the development process, and accuracy over time.

Papers:

Aerial image and IoT sensor data synthesis for ML

Combining multi-spectral images (from planes, drones or satellite) with other sensor data, can help us track health of an individual tree in an orchard. Avishkar and team invented a method to align multiple images, so that we could use distributed compute on big data to analyse 100,000 acres in 15 minutes.

Patent:

  • US10089712B2 - System and method providing automatic alignment of aerial/satellite imagery to known ground features

IoT sensors can produce valuable data, but can also expose user privacy. Avishkar and team invented an algorithm to synthesis IoT sensor data, which protects the original source data privacy, while allowing others to use it with machine learning algorithms to find patterns and make predictions.

Patent:

  •  US11392850B2 - Synthesizing high-fidelity time-series sensor signals to facilitate machine-learning innovations 

orchard.webp
256px-Amazon_logo.svg.png

Ad Targeting using ML

Avishkar worked with the team that built the machine learning based display ad targeting platform at Amazon. Relevant ads means a better user experience and higher ROI for advertisers. In Q3, 2023, Amazon Advertisement generated 12 billion in revenue for the quarter.

Patent: ​

  • US11138631B1 - Predictive user segmentation modeling and browsing interaction analysis for digital advertising 

Image Attribution: By SounderBruce - Own work, CC BY-SA 4.0, https://commons.wikimedia.org/w/index.php?curid=56922594 By Microsoft Corporation - Microsoft Corporation, Public Domain, https://commons.wikimedia.org/w/index.php?curid=94996985 By Pentagram Studio - https://amazon.com/, Public Domain, https://commons.wikimedia.org/w/index.php?curid=130197302 By Microsoft - Screenshot of the app, Fair use, https://en.wikipedia.org/w/index.php?curid=55234258 Pentagram Studio, Public domain, via Wikimedia Commons javatpoint, Public domain, via Wikimedia Commons

bottom of page