Ananya
Barthakur

Software Engineer

Full-Stack Engineer specializing in frontend architecture, distributed systems, and AI integration.

About

I'm a full-stack software engineer with 2+ years of experience at Microsoft, where I specialize in building scalable web applications and integrating AI technologies. My passion lies in creating elegant solutions that bridge complex technical systems with intuitive user experiences. From high-performance backend architectures serving billions of requests to modern frontend interfaces powered by cutting-edge AI, I focus on building software that makes a meaningful impact.

Experience

Microsoft

Software Engineer

Redmond, WA
Jul 2023 – Present
  • â–¸AI Integration: Integrated Generative AI into Microsoft's content platform, boosting efficiency by 80% across 2B+ support pages
  • â–¸Frontend Architecture: Modernized frontend with React, Redux, and Fluent UI, migrating legacy systems while ensuring accessibility and performance standards
  • â–¸Schema-Driven Development: Built form-based UI with JSONForms, reducing authoring time by 40% and structure error rates by 100%
  • â–¸High-Scale Backend Systems: Engineered secure APIs using C#, .NET, Azure Functions, and CosmosDB—serving 15B+ monthly requests with 99.997% uptime
  • â–¸Real-Time Data Pipelines: Led development of metadata pipelines providing system insights for 30+ partner teams, enabling 100% content freshness visibility
  • â–¸DevOps & Infrastructure: Designed secure local development infrastructure with isolated Azure subscriptions and token-based authentication

Microsoft

Software Engineer Intern

Redmond, WA
May – Aug 2022
  • â–¸Built TypeScript + React web app using Microsoft's M365 extensibility SDK, enabling code portability across Teams hosts with 1M+ monthly active users
  • â–¸Created cross-host functionality with shared logic for SSO authentication, calling, and messaging features
  • â–¸Published open-source sample application using official Microsoft Teams JS SDK on GitHub

Machine Learning Research

Research Assistant — Dr. Jean-Baptiste Tristan

Boston, MA
May 2021 – May 2022
  • â–¸Developed ML models predicting compound solubility from cheminformatics datasets (10,000+ molecules) with R² greater than 0.95 accuracy
  • â–¸Implemented feature selection using Lasso regression to identify impactful chemical descriptors and reduce model complexity
  • â–¸Designed modular ML pipeline with cross-validation, hyperparameter tuning, and comprehensive performance metrics
  • â–¸Collaborated with research team to integrate predictive models into computational chemistry workflows

Projects

Atelier - Digital Fashion Wardrobe (WIP)

A sophisticated digital fashion wardrobe app for curating clothing collections.

Key Features

  • â–¸Smart Organization: Categorize items by type, color, brand, fabric with advanced filtering capabilities
  • â–¸Style Discovery: Browse curated fashion inspiration from celebrities like Kendall Jenner and Hailey Bieber
  • â–¸Secure Cloud Storage: All items safely stored with user authentication and personal collections
  • â–¸Elegant Interface: Minimalist, fashion-forward design with responsive layout
ReactTypeScriptSupabaseAI Image ProcessingResponsive Design

PlantPal - AI Plant Care Assistant

A React web application that combines computer vision and NLP to help users identify plants and receive personalized care guidance. The app features dual AI integration with offline fallback capabilities.

Key Features

  • â–¸Smart Plant Identification: Integrated OpenAI Vision API and PlantNet API with fallback logic, achieving 90%+ accuracy in plant identification
  • â–¸AI-Powered Chat Assistant: Implemented conversational AI using OpenAI's GPT-4 for personalized plant care advice and problem diagnosis
  • â–¸Robust Architecture: Built comprehensive offline mode with local plant database, ensuring 100% functionality even when AI services are unavailable
  • â–¸User Experience: Designed intuitive interface with real-time image analysis, confidence scoring, and detailed care instructions
  • â–¸Performance Optimization: Implemented retry logic, error handling, and graceful degradation for enterprise-level reliability
ReactOpenAI APIComputer VisionTypeScriptNode.js

Hartree-Fock Solver

Python implementation for electronic energy approximation and molecular orbital visualization in quantum chemistry applications.

Key Features

  • â–¸Implemented Self-Consistent Field (SCF) algorithm for solving the many-electron Schrödinger equation
  • â–¸Built efficient integral evaluation and matrix manipulation routines for molecular systems
  • â–¸Achieved numerical stability through symmetric orthogonalization and convergence acceleration
  • â–¸Designed modular architecture for different basis sets and molecular configurations
PythonNumPyQuantum ChemistryScientific Computing

Computer Vision: Biomedical Application

Developed CNN and RNN models for breast cancer tissue analysis, enabling automated identification of tumor characteristics in TNBC research.

Key Features

  • â–¸Implemented U-Net and FCN architectures for nuclei segmentation in histopathological images
  • â–¸Achieved greater than 90% accuracy in identifying cancer nuclei morphology and characteristics
  • â–¸Built comprehensive data augmentation pipeline for medical imaging robustness
  • â–¸Designed custom loss functions combining Dice loss and boundary loss for precise segmentation
PyTorchComputer VisionMedical ImagingDeep Learning

Hâ‚‚ Potential Energy Surface

Built Kernel Ridge Regression model with Gaussian Processes to predict molecular potential energy surfaces, using PyTorch for automatic differentiation.

Key Features

  • â–¸Implemented Kernel Ridge Regression with custom kernel functions for molecular property prediction
  • â–¸Utilized Gaussian Processes for uncertainty quantification in energy surface mapping
  • â–¸Leveraged PyTorch's automatic differentiation for gradient-based optimization
  • â–¸Achieved high accuracy in predicting molecular configurations and energy landscapes
PythonPyTorchMachine LearningGaussian ProcessesQuantum Chemistry

TA Application System

Django web application for Boston College streamlining Teaching Assistant applications with secure authentication and administrative workflows.

Key Features

  • â–¸Built full-stack web application using Django framework with PostgreSQL database
  • â–¸Implemented secure user authentication and role-based access control
  • â–¸Designed administrative dashboard for faculty to review and manage TA applications
  • â–¸Created responsive frontend with dynamic forms and real-time application status updates
DjangoPythonPostgreSQLHTML/CSSJavaScript

Technical Skills

Frontend Development

React
TypeScript
JavaScript
HTML/CSS
Redux
Fluent UI
Tailwind CSS

Backend & Cloud

.NET
C#
Node.js
Azure Functions
CosmosDB
REST APIs
Azure Infrastructure

AI & Machine Learning

OpenAI API
Computer Vision
NLP
Python
PyTorch
Scikit-learn
Data Analysis

Tools & Databases

Git
SQL
Django
Azure DevOps
JSON Schema
RESTful Services

Education

Boston College

B.Sc. in Computer Science & Philosophy

Graduated 2023

🏌️ NCAA Division I Golfer📊 SAT 1540

Recommendations

Denise Architetto

2025

Principal Engineering Group Manager (Director M365)

Microsoft

"Ananya is an incredibly bright and driven software engineer with immense potential. From the moment she joined the team, she impressed everyone with how quickly she picked up new technologies and ramped up on a complex domain. Her ability to learn fast, adapt to new challenges, and seek out feedback makes her a standout engineer. Ananya has shown strong capability across both front-end and back-end engineering, demonstrating versatility and a willingness to take on whatever the team needed. She consistently approached her work with thoughtfulness and curiosity—asking insightful questions when working with product managers to ensure a deep understanding of requirements and a clear path to execution. Beyond her technical skills, Ananya is a culture leader. She actively planned team outings and played a key role in building a positive, inclusive, and connected team environment. Her energy, initiative, and focus on team morale made a lasting impact. Ananya is self-motivated, career-focused, and a natural collaborator. I'm excited to see where her career takes her and highly recommend her to any team looking for a talented, adaptable, and inspiring engineer."

Hepcibha Addakula

2025

Principal Engineering Manager

Microsoft

"Working with Ananya has been an absolute pleasure. A fresh breath of energy on the team, she brings curiosity, focus, and unwavering commitment to everything she does. From quickly ramping up on complex projects to leading inclusive team events as part of the morale committee, Ananya consistently delivers with impact. She even mentored an intern gracefully while staying on top of her own commitments. Ananya shows strong ownership across initiatives and is always eager to learn from others, embracing diverse perspectives with respect. Even under challenging conditions, she meets deadlines with urgency and grace. A fantastic teammate and a rising star!"

Jayalakshmi Karanam

2025

Principal Software Engineer

Microsoft

"Collaborating with Ananya has been a truly rewarding experience. She is curious and determined. Her insightful questions regularly uncover blind spots, highlight opportunities for improvement, and bring fresh perspectives that challenge established ways of thinking in a productive and thoughtful manner. Ananya swiftly mastered Azure Data Factory and seamlessly took over my responsibilities in my absence, demonstrating exceptional ownership and adaptability. Her technical proficiency, willingness to learn, and strong problem-solving skills make her a dependable and highly effective team member. Without hesitation, I wholeheartedly recommend Ananya for a software engineer position. She would be an invaluable asset to any organization."

Blog

December 2024

Building a Hartree-Fock Solver: From Quantum Theory to Python Code

A deep dive into implementing a fundamental algorithmn in quantum chemistry and its real-world applications in molecular modeling.

Quantum ChemistryPythonScientific Computing
Read Article
March 2025

Deep Learning for Nuclei Segmentation: A Computer Vision Approach

Exploring CNN and RNN architectures for automated tumor characteristic identification in Triple Negative Breast Cancer research.

Computer VisionDeep LearningMedical Imaging
Read Article

Contact

Let's collaborate on something amazing

ananyabarthakur1@gmail.com