Close

Sanja Simonovikj

Staff Data Scientist @ Indeed | MIT MEng, BSci

Download Resume

About Me

Hello! I'm Sanja, a full-stack Data Scientist with a background and experience in delivering ML/AI end-to-end solutions in both large and small companies, both in research and in industry.

I'm especially interested in recommendation systems, NLP, and two-sided marketplaces.

I enjoy exploring new developments in LLMs and generative AI, while thinking critically about how to apply them in scalable, thoughtful, and safe ways.

Industry Experience

Indeed

Staff Data Scientist

Leading development of AI solutions for structured metadata generation and annotation and improved global matching in Indeed's two sided marketplace

Indeed

Senior Data Scientist

Leading and delivering production-level AI solutions in the Metadata and Taxonomy team powering core Indeed features globally

Indeed

Data Scientist

Developed ML models, tooling, and workflows to improve and expand Indeed's occupation metadata on jobs and resumes in 10+ markets

Microsoft

Data Science Intern

Developed a prototype of an intelligent component for the new Fluid collaborative technology in the Office 365 suite

Qualcomm

Engineering Intern

Deployed tooling for automatic triage of build and test failures for the Secure Systems Group, reducing triaging and debugging time to seconds

Shell

Data Science Intern

Delivered end-to-end Text Summarization pipeline combining extractive algorithms and abstractive Deep Learning models, used by strategy teams

Base Operations

Software Engineering Intern

Backend developer and data engineer in an early-stage start-up for street level threat assessment; implemented core app features and infrastructure (databases, APIs etc)

Black Labs

Software Engineering Intern

Smart Digital Government - developed and deployed a fully functional assistant chatbot using NLP techniques in a start-up environment

Research & Teaching

MIT Department of Electrical Engineering and Computer Science

Graduate Teaching Assistant

Teaching Assistant (TA) for a popular Introduction to Machine Learning course (6.036)

MIT CSAIL - Improbable AI Lab

Research Assistant

Human-aligned features in Deep Learning (Computer Vision) - supervised by Prof. Pulkit Agrawal

IBM Research

Research Intern

Development and improvement of perception and inference modules for Machine Commonsense Reasoning, visual intuitive physics.

MIT CSAIL - ALFA (Anyscale Learning For All) Lab

Undergraduate Researcher

Tree-structured code representation and malware classification - supervised by Prof. Una-May O'Reilly

MIT Electrical Engineering and Computer Science Department

Lab Assistant

Lab Assistant (LA) for a popular Introduction to Machine Learning course (6.036)

Education

Massachusetts Institute of Technology

Jun 2020 - Jun 2021

Master of Engineering - Concentration in Artificial Intelligence

Massachusetts Institute of Technology

Sept 2016 - May 2020

Bachelor of Science in Computer Science and Engineering

Projects

Paper: Metadata Generation and Evaluation using LLMs – Case Study on Canonical Titles

Accepted paper on Recsys 2025 conference. The paper introduces an automated framework using large language models and embedding-based similarity to normalize inconsistent job titles for improved autocomplete suggestions on job search platforms, resulting in higher accuracy and user engagement.

View Paper in Press

LabelLearn

HackMIT 2019 Grand prize winner and Track prize winner. Smart ML data labeling tool that considers consistency between labelers as well as consistency with their previous selves.

View Project

PoseNet Art

An interactive app where the user's motion activates real-time animations and sounds. It is meant to be used for creative and entertainment purposes.

View Project

Community Watch

A web app that allows the citizens of Cambridge (MA) to stay up to date on local crimes and engage in community discussion on crimes in neighborhoods.

View Project

Models of code

Research oriented project studying robustness against obfuscations and adversarial inputs of models of code in two different settings.

View Project

Skills

Get in Touch