Atharva Wandile

Boston, MA ***** Phone: 857-***-****

Email : adzgpz@r.postjobfree.com Website: https://www.linkedin.com/in/atharva-wandile Education

Northeastern University, Boston, MA

• Master of Science in Computer Science GPA: 3.8/4.00 Related courses: Algorithms, Parallel Data Processing, Reinforcement Learning, Data Mining JSS Science and Technology University (SJCE ), Mysore, India

• Bachelor of Engineering in Information Science GPA: 9.14/10.00 Related courses: Data Structures, Object-oriented programming, Machine Learning, Cloud Computing Technical Skills

• Languages: Python, Java, C++, Golang, Scala, SQL, HTML, CSS

• Tools and Technologies: AWS (EMR, Athena, S3), MongoDB, Hadoop, Apache Spark, Redis, Docker, Kubernetes

• Frameworks: Tensorflow, PettingZoo, Flask, Django, JSwing, JUnit, Log4j

• Libraries: Pandas, Keras, PyTorch, Numpy, Matplotlib, OpenAI gym Experience

Research Intern, Lab for Learning and Planning in Robotics(NEU), Boston, MA Jan. 2023 – May 2023

Continuous Macro-Action Learning for RL: Developed continuous macro-action environments for Multi-Agent Reinforcement Learning. Analyzed and tested continuous macro-action PPO algorithm for robotics and autonomous systems.

Comparison of Option-Critic and Actor-Critic Architectures: Achieved state-of-the-art performance by training agents using option- critic and actor-critic algorithms for centralized multi-agent reinforcement learning on four rooms and petting zoo MPE environments.

(Link)

Software Engineer, Redbus (IBIBIO), Bangalore, India Jan. 2020 - Jul. 2021

Big Data Pipelines: Improved customer retention by 10% through the design and implementation of big data pipelines and parallel processing models for customer life cycle management with cross-functional communication with marketing teams for analysis; leveraging AWS cloud and database technologies(MongoDB, Cassandra, Postgres).

Distributed Parallel Processing in Spark: Implemented Spark programs on AWS platform, enhancing efficiency and significantly reducing processing time for weekly and monthly statistical analyses.

Flask and Golang Web APIs: Developed low latency Flask and Golang api’s handling millions of hits per second. Optimized legacy api’s to cut down response time by 50%.

Machine Learning Intern, Allgo Embedded Systems, Bangalore, India Jun. 2019 - Aug. 2019

Tracking Driver Actions: Led a research based project to identify activities of vehicle drivers given video input from dashboard cam and classify activities into distinct classes in realtime using computer vision and deep learning.

Deep Learning and Computer Vision: Analysed and compared multiple models including 2 stream CNNs, LSTM and traditional CV techniques. Demonstrated final model with ability to correctly identify a smaller subset of actions with high accuracy up to 86%.

Software Engineer Intern, Edumerge Pvt. Ltd., Bangalore, India Jun. 2018 - Aug. 2018

Performance Prediction: Designed regression model to predict performance of students of a particular class, given performance trends of previous batch with minimal data (1000 students) for proactive intervention. Algorithm was able to predict performance of students with 2 percent error margin.

Projects

• Distributed Real Time Collaborative Editor: Developed responsive app for a distributed text editor (like google docs) that can support multiple users updating document in real-time and is fault tolerant by leveraging an architecture with data replication management and distributed transactions.

• Distributed Hierarchical Agglomerative Clustering for Music Recommendation: Evaluated distributed k-means clustering with average linkage clustering on Apache Spark using AWS EMR to group similar songs together from million song dataset for music recommendations.

• Java MVC Dungeon Game: GUI application created using Java Swing, that utilizes Kruskal’s algorithm to construct a maze of caves and tunnels emulating locations of a dungeon, given certain configurations. A player must traverse through the dungeon by avoiding monsters, that they can smell from nearby locations, and reach the exit in order to win. The application applies design patterns like Strategy, Factory, Singleton,Dependency Injection etc.(Link)

Contact this candidate