Kaumil Trivedi
A graduate student, and current SAP Cloud Engineer intern with 3 years of experience developing and scaling machine learning solutions to improve customer experience.
Skills
- Data Science
- Machine Learning
- Deep Learning
- Web Scraping
- Software Development
- DevOps
- Python
- Git
- JavaScript
- Tensorflow
- PyTorch
- Flask
- Kubernetes
- Elasticsearch
- Jenkins
- Kibana
- Grafana
- Pingdom
- Prometheus
- CloudFoundry
- MySQL
- MongoDB
- CassandraDB
- Docker
- AWS
Experience
Cloud Engineer Intern
SAP- Maintained operational excellence for SAP Analytics Cloud and SAP DataWarehouse Cloud by ensuring the services ran with 99.5% uptime and meet our service level agreements by using tools like Grafana, Pingdom, Dynatrace and Kibana.
- Collaborated with 20 agile developers, devops and network engineers to diagnose and mitigate mission-critical time-sensitive issues to serve 30000 clients across 10+ globally distributed landscapes.
- Ensured reliable client workloads by managing 100% of all the SAC Capacity and Tenant management processes comprising of business-critical tasks like System/Tenant provisioning and de-provisioning, tenant configuration and feature flag service toggle management.
- Contributed to SaaS level change management processes by performing landscape-wide wave updates via blue-green deployments and AWS scheduled maintenance to ensure the HANA tenants get regular updates and bug-fixes.
- Performed root cause analysis to mitigate recurring incidents and partner with other teams to report crashdumps and fix the underlying bugs.
AI Developer
Areli Commerce Private Limited- Responsible for developing and maintaining a search system using AWS Elasticsearch, handling around 200k queries a month.
- Developed a novel relevance sort algorithm to sort products using custom metrics as required by the business. This was adopted as the default sorting approach of displaying products across the e-commerce site, decreasing the customer attrition.
- Developed a serverless recommender system using the k nearest neighbours algorithm using Flask, AWS Fargate and RDS. Worked alongside the mobile developers to insert event triggers to monitor the health of the application and provide analytics.
AI Developer
Turabit Solutions Private Limited- Worked on development of chatbots and developed API to make the chatbot install software applications on target machine as well as schedule the chatbot to perform a certain function at a time selected by the user.
- Trained ML Models to perform text classification and determine the intent of the user query and trigger the necessary functions required to complete the requested task
Data Science Intern
SoftVan Inc.- Trained ML models for Insurance Fraud Detection, Loan Default Detection, Unsupervised Clustering as well as Object Detection using various architectures such as ResNet, AlexNet, and YOLO.
Education
NFT Marketplace
Created a service-oriented REST architecture based marketplace web app with CI/CD, load testing and dashboarding. Implemented the Infrastructure-as-a-Code (IaaC) paradigm and scaled the application to 5000 concurrent users and 2800 requests/second using simulated load testing via Gatling.
Crime Hotspot Prediction
Experimented to utilise a novel Convolutional LSTM model to extract spatio-temporal features to predict crime hotspots over Vancouver city with 82% recall and 71% precision. Worked on developing a data collection api to extend model training for multiple cities and predit crime-wise hotspots.
Aviation Safety in Canada
Collaborated in a team to use Spark, AWS Lambda, S3 and Glue to implement an ETL pipeline to scrape and process civil aviation accident and incident records on a weekly basis and AWS Quicksight for dashboarding. Developed an unsupervised system using K-Means clustering algorithm to determine the possible features leading to fatalities/injuries in an accident.
Emof_AI
Emof_ai is a web API which takes a sample video as an input, detects all the faces in each frame of the video and performs classfication. It classifies the emotion of the face into 1 of 8 emotions viz anger, disgust, fear, happy, sad, surprise, neutral and none(this is when there are no faces detected in the frame at all and hence none means no emotion detected in the frame at all). It also classifies the gender of the person. In addition to that, it also classifies the age group of the person into 1 of 4 age groups viz adult, child, old and youth.
Wait! There's more..
See all Projects for more!
Advanced MySQL: MySQL Data Analysis & Business Intelligence
Issuing Organization: Udemy Inc.
Validity: April 2021 - Present
I got to learn how to employ MySQL to solve advanced business problems like traffic sources, website performances, channel portfolio management, seasonality, product and user analysis
AWS Certified Developer Associate
Issuing Organization: Amazon Web Services
Validity: November 2020 - November 2023
I got to learn the basics of AWS and how to deploy CI/CD pipelines as well as serverless development on AWS, using tools like Lambda, API Gateway.
Deep Learning Specialization by deeplearning.ai
Issuing Organization: Coursera
Validity: March 2018 - Present
I completed 5 courses included in this specialization pertaining to Neural Networks, Convolutional Neural Networks and Sequence Models. Furthermore I also worked on several mini projects such as music generation and object detection.
Machine Learning by Stanford University
Issuing Organization: Coursera
Validity: June 2017 - Present
This was the first course I took to learn concepts of Machine Learning. I learnt various concepts like Loss algorithm, Linear and Logistic Regression, Support Vector Machines, Random Forests. Furthermore, I also learnt the theory of Neural Networks
Spark and Python for Big Data with PySpark
Issuing Organization: Udemy
Validity: September 2019 - Present
I learnt how to use PySpark client api to leverage the power of Apache Spark and solve big data problems. I learnt how to use Spark 2.0 DataFrame API as well as use the Spark Mllib library to train machine learning models.
Taming Big Data with Apache Spark and Python - Hands On!
Issuing Organization: Udemy
Validity: August 2019 - Present
This course taught me the mechanism behind Big Data. I learnt what is Hadoop and YARN, in addition to Apache Spark
Wait! There's more..
See all Certifications for more!
Paper - A Hybrid Binary Classifier for Pattern Classification
My interview
April 2020
Checkout my interview at R3plica where I share how I started my professional career in AI, current breakthroughs in AI which excite me and various domains I wish to get AI implemented in.
