Astarag Mohapatra
Machine Learning Engineer at Evidium
San Francisco, California, United States
Summary
🤩
Rockstar🎓
Top SchoolAstarag Mohapatra is a Machine Learning Engineer based in San Francisco with 6 years of experience blending research-grade reinforcement learning and production-focused data engineering. He has contributed to high-profile open-source finance projects like FinRL (including a Binance data ingestor and Optuna hyperparameter tuning) and extended FinRL-Meta with Google Trends integration to enrich market signals. His background spans academic RL research comparing agent and animal neural signals, biotech analytics at BeiGene where he built a BERTopic- and GPT-based sentiment pipeline, and production ML tooling using Ray, RLlib, Docker, Kubernetes and GCP. Comfortable moving models from notebooks into scalable pipelines, he pairs a researcher’s curiosity—sparked by AlphaGo—with pragmatic engineering that has reduced costs and sped deployments in prior roles.
6 years of coding experience
1 year of employment as a software developer
Master's degree Computational Science, Master's degree Computational Science at Indiana University BloomingtonBachelor of Technology - BTech Major in Mechanical engineering and Minor in Electronics and communication engineering, Bachelor of Technology - BTech Major in Mechanical engineering and Minor in Electronics and communication engineering at National Institute of Technology Rourkela
Github Skills (20)
apim10
dsym10
python10
finance10
pandas10
binance10
fintech10
api10
data-processing10
deep-reinforcement-learning10
jupyter-notebook10
data-acquisition10
data-integration10
optuna10
data-analysis10
Programming languages (3)
Github contributions (5)
AI4Finance-Foundation/FinRL
Sep 2021 - Dec 2022
FinRL: Financial Reinforcement Learning. 🔥
Role in this project:
Back-end Developer & Data Engineer
Back-end Developer & Data EngineerContributions:3 reviews, 49 commits, 14 PRs in 1 year 3 months
Contributions summary:Astarag's primary contribution involves developing a Python script to download Binance cryptocurrency data within a specified date range. This script leverages the Binance API and utilizes libraries like requests, json, and pandas to retrieve and process the data into a usable format. The user's code also includes a class to handle the data retrieval process. Additionally, the user optimized hyperparameters using Optuna, indicating work on the data processing pipeline and model training process.
stable-baselinesdrl-frameworkdeep-reinforcement-learningsecfinance
AI4Finance-Foundation/FinRL-Meta
Nov 2021 - Aug 2022
FinRL®-Meta: Dynamic datasets and market environments for FinRL.
Role in this project:Data Scientist
Data ScientistContributions:1 review, 12 commits, 2 PRs in 9 months
Contributions summary:Astarag contributed to the project by integrating Google Trends data into the FinRL framework and demonstrating its usage with the DOW Jones index. The user's work involved the modification of existing notebooks to incorporate and process external data sources. The contributions include the implementation of a custom data processor to integrate trends data and adapt FinRL to incorporate it, showing the user's ability to extend the existing framework for new analyses. This demonstrates a focus on expanding FinRL's data ingestion capabilities.
data-drivenfinancialdrl-trading-agentsmetaversereinforcement-learning
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.