Puneet Singh Ludu

puneet.ludu@gmail.com | New York, NY | +1-(716) 867-4344

Education

Master of Science in Computer Science
State University of New York, Buffalo, NY
2014
B. Tech. in Computer Science
Jaypee Institute of Information Technology, Noida, India
2010

Skills

Languages

Python • Java • C/C++ • Bash • Javascript • HTML • SQL

Frameworks

PySpark • Keras • Metaflow • KubeFlow • TensorFlow • PyTorch • MongoDB • FastAPI • Django

Experience ~11 years

Machine Learning Engineer

Zillow | Sep 2021 - Present | Remote ~3 Years

Interactive CMA & Realtime Valuation

Django, DocumentDB, PyTorch [Siamese Neural Network]

Architected and led the end-to-end development of an interactive Comparative Market Analysis (CMA) platform with Realtime Valuations, Property Embeddings and Comps API, providing agents and buyers with data-driven tools to support home pricing, enhancing client decision-making and driving potential revenue through valuation services.

Impact: 0 to 1 project to boost engagement and satisfaction, paving the way for new revenue streams

Zestimate Infrastructure Modernization

Python, Terraform, AWS, Kubeflow, Metaflow, Docker, Gitlab CI

Led the modernization of a critical valuation ML infrastructure, transitioning to more cost-effective, containerized technologies, resulting in substantial annual cost savings and enhanced system scalability.

Impact: Achieved operational improvements and annual cost savings of $500k.

Technical Innovation & Team Collaboration

Integrated advanced machine learning tools into team workflows and established coding standards, significantly enhancing collaboration and experiment tracking capabilities. Contributed to open-source projects.

Impact: Improved overall team efficiency, code quality. Reduced On-Call alerts by 95%

Leadership & Mentorship

Managed interns and Mentored new hire, fostering technical skill development and guiding them through project contributions.

Machine Learning Engineer

OkCupid | May 2020 - Sep 2021 | New York City ~1.5 Years

Discount Optimization

Python, Keras, TensorFlow, Weights and Biases [Wide&Deep]

Lead the efforts to optimize subscription pricing(discounts) to maximize the revenue for OKCupid, Implemented end-to-end ML pipelines, feature engineering, modelling, alerting etc.

Impact: Increased overall revenue by 6% through A/B testing against assigned prices

Machine Learning Engineer

FactSet | Jan 2018 - May 2020 | New York City ~2.5 Years

Speaker Identification

Python, Keras, Spectrograms, CNN

Developed a system to identify speakers from live audio during company calls (e.g., earning calls) using spectrograms and CNN-based deep learning models.

Private Company Fact Extraction

Python, Keras, Sagemaker, ELMo, BiLSTM, Blazingtext

Led the development of a system to extract full company names, key people, their titles, and biographies from 1.6 million crawled and cached websites of private companies.

Similar Concepts & Type Ahead

Apache Spark, Python, Java, Word2Vec, Distributed Trie

Developed concept suggestion system based on queries extracted from news articles and PDF reports. Implemented distributed trie-based autocomplete/auto-suggest feature for the FactSet terminal.

Trending Topics & Formula Ranking

Python, Apache Spark, Doc2Vec, N-gram Language Models

Built system to identify trending topic clusters from recent news articles. Developed user clustering and formula ranking system for the type-ahead feature of FactSet terminal.

Software Engineer

FactSet | Apr 2015 - Sep 2016 | New York City Metropolitan Area ~1.5 Years

Duplicate Document Identification

Java, Shingling, Vector Space Models

Duplicate Document Identification

Java, Shingling, Vector Space Models

Developed a service to identify duplicate documents in real-time from a large stream of documents using shingling and vector space models.

Earnings and Stock Correlation Analysis

Python, Java, Logistic Regression

Built a system to analyze correlation between social media sentiments and company earnings/stocks using logistic regression.

Research Engineer (Machine Learning / Big Data)

Tata Research Development and Design Centre (TRDDC) | Jul 2011 - Aug 2013 | Noida Area, India ~2 Years

Time Series Analysis on Big Data

Stream Processing, Time Series Analysis, Pattern Mining

Worked on a research project involving stream fusion and time series analysis of sensor data. Responsible for conceptualizing and implementing various algorithms involving interdependent causality detection, pattern mining to extract interesting information and patterns.

Data Harmonization Framework (DHF)

MapReduce, Apache Pig, ETL, Big Data

Implemented the next generation ETL framework that exploits the power of map-reduce and big-databases to fuse incongruous enterprise data from disparate sources in near real time to give one harmonized view of the data and thus making analytics simpler and faster.

Conceptualized an end-to-end ETL tool built over DHF capable of generating Apache Pig scripts useful for making Harmonization process easy and seamless.

Developer (Assistant System Engineer)

Tata Consultancy Services | Dec 2010 - Jun 2011 | Thiruvananthapuram Area, India 7 Months

Trainee Evaluation System

PHP, jQuery, Moodle

Led team of two in the development of 'Trainee Evaluation System' deployed in the TCS Trivandrum training center. Created the whole system from scratch using PHP and jQuery, and was responsible for integrating 'Moodle' into this evaluation system.

Resource Planning and Scheduling System

Developed solution for the long standing problem in the training center of managing resources and scheduling them in optimal and fail-safe way. Also worked as a guest author in the "Linux and FOSS" section of the training material.

Publications

Personal Projects

Organizer @ MUFin

Committee member, organizer and reviewer to the MUFin Workshop at top conferences, focusing on innovative approaches to modeling uncertainty in the financial sector (AAAI2023, PKDD2022)

Resume Analyzer

Resume analysis tool that uses OpenAI's API to improve resume and prepare an impactful introduction script

Lotion

Unofficial Notion.so Desktop app for Linux (2K+ GitHub stars / 60K+ Clones & Downloads)

Romadeva

Tool to convert Roman script to Indic(Devanagari) script (Used by https://translatorswithoutborders.org)

jTextBrew

A JAVA library for fuzzy string matching, based on TextBrew algorithm by Chris Brew

Quena

Question and Answering system – Indexed 1.6 Million Wikipedia documents, designed a question parser and a ranking algorithm based on popularity. (Apache Solr, NER, POS tagger)