Apple

Team: Machine Learning Platforms Team, AI/ML organization

Machine Learning Engineer

University of Wisconsin-Madison

COMP SCI 760: Machine Learning (Fall 2022)
COMP SCI 540: Introduction to Artificial Intelligence (Fall 2022)
COMP SCI 639: Foundations of Data Science (Spring 2022)
COMP SCI 540: Introduction to Artificial Intelligence (Fall 2021)

Computer Science Grader

Team: Machine Learning Platforms Team, AI/ML organization
❏ Integrated T5 large language model pre-trained internally, finetuned for text summarization to achieve 0.86 BERT score.

Machine Learning Engineering - Intern

Team: Core Engineering, Enterprise & AI solutions 

❏ Implemented FastText model to improve retrieval of articles in the Component-Issue search
❏ Prototyped text-to-speech module for Apple's support guides to improve accessibility for customers with reading and learning disabilities.

Team: AppleCare & Retail Digital, Global Business Intelligence organization

Software Engineer

Amazon

Team: Customer Behaviour Analysis, Automated Advertising organization

❏  Worked alongside research scientists in transforming their research work to a large-scale, automated, production-grade Machine Learning Attribution model.
❏  The model is being used to guide the apportionment of Amazon’s budget of over $10 billion on various advertising media.
❏  Single-handedly created the low-level design, implemented and integrated the snapshot training and featurization modules to process over a billion records per day and scale to handle spikes in traffic - during sales and holiday seasons.
❏  Optimized the machine learning pipeline to reduce the model’s execution time by 75% when measured on the US marketplace keeping the machine's configurations the same. 
❏  Operational Excellence tasks: reduced the ticket count of the on-call by 1 Sev-2 and 5 Sev-3 tickets weekly on an average 
❏  Technology stack: Scala, Spark, Omniflow, DJS, AWS S3, EMR, Dynamo DB, EC2, SWF

Software Development Engineer (SDE)- Intern

Team: Social Ads, Automated Advertising organization

❏  Improved anomaly detection in Amazon’s ads performance data from Facebook, Twitter, Pinterest, and other vendors. 
❏  Combined the z-score and dynamic-range methods to better account for the variations in customer interaction patterns reducing false anomaly alarms by 60%.
❏  Implemented a logger plugin and designed a dashboard to display anomaly and trouble ticket data in an organized, accessible, and user-friendly manner for marketing managers.
❏  Technology stack: Java, JavaServer Pages, CSS, JavaScript, AWS S3, Frameworks: Spring, Mockito, API: Fluxo

Software Development Engineer (SDE) - Intern

DRDO, Ministry of Defence, Govt. of India

Summer Intern

Kriti is a Machine Learning Engineer with Apple in ML Platforms, AI/ML. Her industry experience of 3 years lies in developing large-scale, automated, production-grade systems. Before this, she completed her Master's in Computer Science at the University of Wisconsin-Madison, specializing in Machine Learning- CV and NLP. She has also interned with Amazon in the Advertising organization, where she worked on the Machine Learning Attribution model.

Skills: Python(Pytorch, TensorFlow and statistics libraries), C++, Scala, Spark, Java, and AWS (S3, EMR, DynamoDB, EC2, SWF, Athena, and QuickSight), Git

taplio

Kriti Goyal's Linkedin Analytics

Kriti Goyal

Performance Score

Ready to grow your LinkedIn presence?

taplio

.css-6ytdur{background-image:linear-gradient(284deg, rgba(39, 43, 72, 1) 0%, rgba(33, 47, 183, 1) 100%);color:transparent;-webkit-background-clip:text;background-clip:text;}Kriti Goyal's Linkedin Analytics

Kriti Goyal

Performance Score

Ready to grow your LinkedIn presence?

Kriti Goyal's Linkedin Analytics