Hi, I'm Mihir 👋

Machine Learning Engineer | ML Systems • Time-Series • Reliability

I build production-oriented ML systems where labels are missing, noise is high, and failures are expensive. My focus is on how ML behaves under real-world constraints, not just model accuracy.

What I Work On

Label-free & weakly supervised ML problems

Time-series modeling and drift detection

Full ML Lifecycle: Preprocessing, Training, Tuning, Validation & Testing

Offline learning + deterministic online systems

Failure modes, alert fatigue, and explainability

I prefer statistical ML and explicit objectives over opaque black-box models when reliability matters.

Featured Project — BLACKICE ❄️

Hybrid ML System for Streaming Regime Shift Detection

BLACKICE detects persistent behavioral drift in infrastructure metrics using a hybrid ML architecture.

ML Problem (Constraints)

ML Approach (Solution)

No labeled data

Streaming statistical baselines (Welford)

Highly noisy, bursty signals

Offline optimization of decision boundaries

False positives > delays

Custom SRE-weighted loss function

Black-box opacity

Persistence-aware detection (not point anomalies)

Impact: ~80–90% noise filtered, <1% false positives, O(1) memory, tested on 8GB+ production data.

🔗 Repo: https://github.com/Mihirmaru22/blackice

Other Projects

Fraud Detection ML System 🛡️

End-to-End Pipeline for Financial Anomaly Detection

Robust Pipeline: Modular architecture spanning data ingestion, preprocessing, and model training.

Imbalanced Data Handling: Specialized strategies for highly skewed class distributions, focusing on Precision-Recall optimization over raw accuracy.

Production Focus: Designed to minimize expensive false negatives while maintaining system reliability in anomaly detection.

🔗 View Code

Local Fire Weather AI 🌲

Real-time forest fire risk assessment API

Precision Modeling: Ridge Regression pipeline with automated feature scaling.

Production Ready: Serialized Joblib model served via RESTful Flask interface.

Deployment: Container-friendly structure for AWS/Render.

🔗 View Code

Technical Skills

Tech Stack

Currently Learning