Manish Tiwari


🚀 Current Projects & Roadmap

What I'm building and learning right now — focused on open source, ML systems, and deployment pipelines.

🌟 Open Source Contributions

sktime
Contributing to dataset and benchmarking infrastructure for time series machine learning library, unified API for forecasting and classification.
Python Time Series Benchmarking
CHAOSS/augur
Open source project for measuring community health and sustainability metrics in software development.
Python Metrics OSS Health

📊 Production Model Drift Monitoring System

Feb 2026 | Active Development
Designed and built an end-to-end MLOps prototype to monitor model drift in production-like settings. The system tracks changes in prediction distributions over time and triggers alerts when significant drift is detected.
  • FastAPI service for model inference with prediction logging
  • Drift detection using statistical methods (PSI, KS test)
  • Interactive Streamlit dashboard with Plotly visualizations
  • Discord webhook alerts for threshold-based notifications
  • Docker containerization with GitHub Actions CI
FastAPI Streamlit Scikit-learn Docker GitHub Actions Plotly
⚡ Note: This is a prototype system focused on demonstrating end-to-end monitoring. Future improvements include better scalability, feature-level drift tracking, and performance benchmarking.

🤖 Custom Language Model Training

Jan 2026 | Research & Learning
Trained a lightweight 4.2M-parameter language model using PyTorch to understand the end-to-end training workflow.
  • Implemented training loop, loss tracking, and evaluation
  • Experimented with hyperparameters (learning rate, batch size, sequence length)
  • Analyzed training behavior using loss curves
PyTorch Python Transformers
🎯 Note: This project focuses on understanding training mechanics and model behavior rather than achieving state-of-the-art performance.

📚 Learning Focus

Currently diving deep into:

  • ML systems architecture and design patterns
  • Production deployment strategies for ML models
  • Monitoring and maintaining ML systems in production
  • Cost optimization for inference at scale

Updated: February 2026