Leela Prabhu
ML EngineerSr. Software Engineer at Planet
Planet
AI is analyzing your overall score…
Identifying your key strengths…
Evaluating your skill match against the job requirements…
Assessing your cultural and operational fit
Sr. Software Engineer at Planet
AI is analyzing your overall score…
Identifying your key strengths…
Evaluating your skill match against the job requirements…
Assessing your cultural and operational fit
- Interests: Machine Learning, Data Science, Distributed Systems - Please contact me by email: leelaprabhu93@gmail.com
University of Southampton
Master’s Degree, Artificial Intelligence
January 1, 2015 – January 1, 2016
The University of Edinburgh
Master’s Degree, Computer Science
January 1, 2014 – January 1, 2015
National Institute of Technology Karnataka
Bachelor’s Degree, Electronics and Communications Engineering
January 1, 2010 – January 1, 2014
Planet
Senior Software Engineer
October 1, 2025 – Present
San Francisco Bay Area · Hybrid
Amazon
Sr. SDE
December 1, 2023 – October 1, 2025
Amazon
Senior Software Engineer
March 1, 2023 – December 1, 2023
Amazon
Software Development Engineer
November 1, 2019 – March 1, 2023
Capital One
Senior Software Engineer - Machine Learning
July 1, 2019 – November 1, 2019
Capital One
Software Engineer - Machine Learning
September 1, 2017 – July 1, 2019
Schrödinger
Machine Learning Engineer
February 1, 2017 – August 1, 2017
New York City Metropolitan Area
Gill Instruments Pvt. Ltd. - India
Intern
May 1, 2013 – July 1, 2013
Bangalore
Indian Institute of Science
Intern
May 1, 2012 – July 1, 2012
Bangalore
MSc Thesis- Gap Gene Expression in Drosophila Development
June 1, 2016 – Present
Created a Gaussian Process based Bayesian Optimiser to fit a 66 parameter model to the Gap Gene Circuit of Drosophila. The aim was to minimise the number of function evaluations of the optimiser with respect to previous work using Island based Evolutionary Strategies.
Image Classifier
January 1, 2016 – Present
Studied various image classification algorithms by testing on several datasets- MNIST, CIFAR, MNIST extended and Traffic sign datasets. Developed a novel classifier by using multiple CNNs for feature extraction and SVM for classification. Used Keras, Tensorflow, MxNet, scikit-learn and OpenCV (for image preprocessing and dataset extension)
Kaggle Home Depot Contest
January 1, 2016 – Present
Participated in a data mining based Kaggle contest, securing a place in the top 25%. Applied data visualisation methods to understand the data, followed by information retrieval and ensemble methods to classify the test cases. The project included usage of NLP libraries in Python, scikit-learn to implement the classifier and pandas for data manipulation.
MSc Thesis- Designing a Run-time Adaptive Compression Algorithm for Stream-based Workflows
June 1, 2015 – Present
Studied means to improve the execution time of dispel4py workflows by incorporating data compression. dispel4py is a Python framework that manages stream based data intensive scientific workflows.
KNN Join using Hadoop
January 1, 2015 – Present
Implemented the paper "Efficient Processing of k Nearest Neighbor Joins using MapReduce" by Lu et. al. Used Hadoop with Python for implementation.
Street View and Flickr Image Viewer
September 1, 2014 – Present
Developed a Google Street View like application in Java. The project also involve object oriented design concepts and use of JavaFX Scene Builder. Using Flickr API, an image viewer was also designed.
Synchronous GHS Implementation for Distributed MST
September 1, 2014 – Present
Implemented a Synchronous GHS algorithm for Distributed MST. Used concepts of object oriented programming and distributed systems. Java was used as the programming langauge
BTech Project- DWT based Compression on FPGA
July 1, 2013 – Present
Designed an architecture for implementing a 3-level Discrete Wavelet Compression system for images on a Xilinx FPGA. The code was written in VHDL.
Sequence Models
Coursera
June 24, 2026 – Present
Improving Deep Neural Networks: Hyperparameter tuning, Regularization and Optimization
Coursera
June 24, 2026 – Present
Cultural Fit Analysis
The candidate's diverse project portfolio, ranging from theoretical research (MSc theses) to practical applications (Kaggle, image classifier), indicates a strong curiosity and a proactive learning attitude. Their experience at large organizations like Amazon and Capital One suggests an ability to adapt to structured environments. The target role of ML Engineer aligns well with their academic background and professional experience, particularly their roles focused on Machine Learning at Capital One and Schrödinger. The breadth of technologies mentioned across projects (Keras, TensorFlow, MxNet, scikit-learn, OpenCV, Hadoop, Python NLP libraries, Java, VHDL) suggests adaptability and a willingness to explore different tools and paradigms.
Soft Skills & Operational Fit
The candidate's project descriptions indicate an ability to tackle complex problems independently and a strong academic foundation. The progression through Senior Software Engineer roles at Amazon suggests strong operational capabilities and leadership potential. However, specific soft skills like teamwork, communication style, or problem-solving approach in a collaborative setting cannot be fully assessed without interview data.