Achyudh Ram
Software Development Engineer at Amazon
Old Toronto, Ontario, Canada
Summary
👤
Senior🎓
Top SchoolAchyudh Ram is a Software Development Engineer with 10 years of experience building scalable, ML-driven systems for supply chain and forecasting at Amazon and production backend platforms at Shopify and Intuit. He blends deep learning, information retrieval and distributed systems—grounded in an M.Math. from the University of Waterloo—to deliver latency-sensitive, production-ready solutions such as predictive auto-scaling and demand forecasting. His research background in computational linguistics and software analytics complements hands-on engineering, evident in contributions to PyTorch-based document classification tooling (castorini/hedwig) involving training pipeline and negative-sampling implementations. Based in Toronto, he’s equally comfortable optimizing big-data query execution and shipping robust backend services, with a practical knack for merging research ideas into production code.
10 years of coding experience
3 years of employment as a software developer
BITS Pilani, Birla Institute of Technology and ScienceM.Math. (Thesis) Computer Science, M.Math. (Thesis) Computer Science at University of Waterloo
English, Tamil, Hindi
Stackoverflow
33reputation
5kreached
0answers
1question
Github Skills (10)
pytorch10
machine-learning10
deep-learning10
trainings10
python10
modeling10
dendrogram6
cluster-analysis6
numpy6
plotly6
Programming languages (6)
Github contributions (5)
castorini/hedwig
Mar 2019 - Jun 2020
PyTorch deep learning models for document classification
Role in this project:
Back-end Developer & ML Engineer
Back-end Developer & ML EngineerContributions:70 commits, 33 PRs, 12 pushes in 1 year 3 months
Contributions summary:Achyudh's primary contribution involved merging code from another repository (`castorini/castor`) into the `hedwig` project. This includes substantial changes to the `nce/nce_pairwise_sm/train.py` file, implying involvement in the training of a deep learning model. The code changes suggest the implementation of a model for document classification using PyTorch, potentially incorporating techniques such as negative sampling and margin ranking loss. Further commits show modifications to the project's build configuration and dependency management.
pytorchdeep-learningmulti-label-classificationdocument-classificationmachine-learning
omniocular/omniocular
Mar 2019 - Nov 2019
A PyTorch-based framework for building deep learning models on code
Contributions:98 commits, 36 PRs, 17 pushes in 8 months
deep-learningpytorchdeep-learning-modelsmachine-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.