Close

Anshul Patel

Software Engineer | Machine Learning | Data Science

Download Resume

About Me

I'm a Software Development Engineer II at Amazon Web Services in New York, currently leading core product infrastructure for Kiro Autonomous Agent - AWS's autonomous AI development agent. I enjoy building scalable systems that bridge the gap between cutting-edge AI and practical developer tools.

My expertise spans full-stack development with TypeScript, Python, and Java, along with deep experience in AWS cloud infrastructure including CDK, Lambda, DynamoDB, and distributed systems. I've architected solutions that improved performance by 40% and scaled platforms to support 20,000+ users at launch.

Beyond my day job, I'm passionate about Machine Learning, NLP, and building side projects that solve real problems. I hold a Master's in Computer Science from NC State University (4.0 GPA) and love mentoring engineers and driving operational excellence initiatives.

Experience

Amazon Web Services

Software Development Engineer II

  • Led core product infrastructure for the Kiro Autonomous Agent (AWS's autonomous AI development agent), owning metering and billing platforms, onboarding flows, and third‑party integrations
  • Scaled production to support 20,000 users at launch for re:Invent 2025

Amazon Web Services

Software Development Engineer I

  • Architected materialized view processing enhancements including reverse relationships, one-to-many views, and V2 rearchitecture with resource association integration, enabling complex document aggregation and resource link traversal for AWS CodeCatalyst teams while improving performance by 40%
  • Established full ownership of business metrics infrastructure by implementing cross-account S3 replication, operational tooling, monitoring, and event processing integration, ensuring reliable data pipeline operations for CodeCatalyst's business intelligence capabilities
  • Led operational excellence and mentorship initiatives through weekly 1:1s with new engineers, ORR/COE documentation, and intern project support including end-to-end tracing dashboard development, achieving 62% operational backlog reduction

Amazon Web Services

Software Development Engineer Intern

  • Utilized Typescript to develop a JSON Schema Linter CLI, which provided authors with guidance on best practices and resulted in a 70% reduction in review labor hours.
  • Developed a Java SDK and integration tests for the Code.AWS Rococo Eventing System.

North Carolina State University

IT Assistant

  • Assisted students, faculty, and staff with technical support and troubleshooting for computers, printers, and other hardware and software in the Student Center
  • Maintained inventory and placed orders for computer hardware and software as needed
  • Set up and configured computers, laptops, and other equipment for events and meetings in the Student Center
  • Provided support for the Student Center's audio-visual equipment, including projectors, microphones, and sound systems
  • Collaborated with other IT professionals to resolve technical issues and implement new systems and technologies
  • Assisted with training and orientation for new Student Center staff on IT-related systems and procedures

CloudOffis

Associate Engineer

  • Automated the process of extracting relevant data from SMSF documents, yielding up to 80% reduction of work time per document.
  • Transformed classification model using Active Learning techniques to detect and sustain both concept drift and data drift to adapt new documents as they turn up.
  • Implemented dynamic multiprocessing in the pipeline, achieving a reduction in process time by 30%.

Knowarth Technologies

Machine Learning Intern

  • Developed a multi-class classification model using Ensemble techniques for 1000+ unstructured SMSF documents distributed over 30 classes, attaining over 95% accuracy.
  • Orchestrated the migration of the REST-based APIs to a cloud-based distributed system using AWS SQS and S3 Buckets.
  • Evaluated different Object Detection architectures namely YOLOv3, YOLOv4, RetinaNet, CascadeNet, and Detectron 2 to identify borderless tables and cells with a custom dataset.

Knowarth Technologies

Project Intern

  • Spearheaded a proof of concept model for extracting page location of keywords from Australian SMSF documents.
  • Implemented a Flask Restplus API with Swagger UI connected to MySQL Database to track down details of the uploaded file along with its status and results.

Speech Research Group, Nirma University

Research Assistant

  • Worked on Speech Processing and Audio Analysis Research Projects using techniques from Machine Learning and Deep Learning under the guidance of Professor Sapan Mankad.

Education

North Carolina State University

2021 - 2022

Masters of Computer Science

CGPA: 4.0/4.0

Relevant Courses: Software Engineering, Artificial Intelligence, Database Management System, Computer Networks

Nirma University

2016 - 2020

Bachelor of Technology in Information Technology

CGPA: 8.57/10.0

Relevant Courses: Linear Algebra, Data Structures, Theory of Computation, Design and Analysis of Algorithms, Machine Learning, Information Retrieval Systems, Deep Learning

Publication

IFSC : A Database for Indian Folk Songs Classification

Advances in Intelligent Systems and Computing, Springer Singapore

The paper was presented in the 25th International Symposium on Frontiers of Research in Speech and Music (FRSM 2020), jointly organized by National Institute of Technology, Silchar, India, during 8–9 October 2020.

Projects

InvestNotes project thumbnail

InvestNotes

Built a multi-market portfolio tracker (NSE, NASDAQ, NYSE) with Next.js 14, Supabase, and TradingView charts, supporting real-time P&L tracking, cash allocation, and transaction management — deployed on Vercel.

  • Architected serverless business logic using Supabase Edge Functions and cron jobs for transaction processing, dynamic price caching via Yahoo Finance, and automated daily portfolio refresh.

View Project
MachineHack Hackathons project thumbnail

MachineHack Hackathons

The repository contains notebooks of various MachineHack Hackathons covering multiple domains of Machine Learning and Deep Learning Worlds:

  • Regression Problems
  • Classification Problems
  • Time Series Problems
  • Range Prediction Problems

View Project
BOTAnshul chatbot resume project thumbnail

BOTAnshul

  • Redesigned the future of employer-employee interaction in form of a personalized chatbot resume using python's open-source library Rasa.
  • Deployed the mini version of me on a personal website using Heroku docker services, making conversations available 24×7 and accessible from any part of the world.

View Project
automeans Python library project thumbnail

automeans

  • Python Library for automating the scikit-learn K-Means Clustering Algorithm by optimising the selection of number of clusters.

View Project
Handy Cricket game project thumbnail

Handy Cricket

  • The game was made using powers of Open-CV and Keras library to identify hand signals denoting runs scored.
  • The game would be played between you and the computer.
  • Score more than the computer to win the Game.

View Project
PhotoEditor OpenCV project thumbnail

PhotoEditor using OpenCV

  • Apply Instagram-like filters or adjust/edit your Images using commands of OpenCV Python Library.
  • Created a UI using Gradio Library to share the project.

View Project
Speaker Diarization project thumbnail

Speaker Diarization

  • Investigated state-of-art methods and speech processing techniques used in preexisting Speaker Diarization systems to identify the number of speakers and segmenting their respective speech time in conversational audio signals.
  • Devised a novel framework and developed a model on features extracted from ‘The ICSI Meeting’ and ‘The AMI’ corpus using pyAudioAnalysis for segmentation and Hierarchical clustering for recognizing speakers.

View Project
Slytherin genetic algorithm game project thumbnail

Slytherin Game using Genetic Algorithm

  • Developed a Genetic Algorithm for the old Snake Game using pygame library, resulting in a better score for computers than humans after mutating through a series of generations.

View Project
AMBeats music player project thumbnail

AMBeats: Android Music Player with Recommender System

The project involves developing an android app that displays all the songs stored in the local storage that can be played using a minimalistic user interface. The interface allows users to like the songs they hear and those songs are then saved onto an online database. These liked songs were then compared with other users who liked similar songs to provide new recommendations using Machine Learning algorithm.

View Project
ASVspoof playback attack detection project thumbnail

Playback Attack Detection for Speaker Verification Systems

The project was a research-oriented work that involved extracting cepstral features from audio obtained from the ASVSpoof 2017 benchmark dataset, which were then analyzed to find out which features better affect the decision of whether the spoken speech is genuine or spoof.

View Project
Next-Word Prediction NLP project thumbnail

Next-Word Prediction

The project involves developing a N-gram probabilistic model that predicts the next possible words based on the entered word or a sentence by the user. The prediction made by a pre-trained model trained on the text of multiple storybooks.

View Project
Named Entity Recognition NLP project thumbnail

Named Entity Recognizer Guide

The project utilizes a combination of python and natural language processing to create a custom model that helps machine classify text based on person, location, money, time, date and much more. We show the use of Bidirectional LSTM and BERT Models to overcome the problem. The project can be launched as demo version using Gradio.

View Project

Skills

Certifications

Machine Learning and Deep Learning

Data Science

Software and Tools

Hobbies

Get in Touch