Aditya Tiwari

Aspiring Machine Learning Engineer

Building machine learning systems and documenting the engineering journey.

AdityaLab

"A living engineering notebook documenting my journey toward becoming a Machine Learning Engineer."

Every project, engineering note, and case study reflects real work, real learning, and continuous improvement.

Engineering Philosophy

Systems Thinking

Machine learning models are only one component of a larger software system. Focus on deployment, APIs, infrastructure, validation, and maintainability.

Reproducibility & Maintainability

Prioritize modular code, reproducible experiments, clean interfaces, validation, and maintainable pipelines.

Learning in Public

Document experiments, failures, trade-offs, and engineering decisions to create a transparent learning record.

Currently Building

Loan Approval Prediction System

  • Status: Building Terraform infrastructure
  • Last Updated: July 2026
  • Next Milestone: Containerize inference API

Now

  • 📖 Reading: Designing ML Systems
  • 🧠 Learning: Terraform
  • ⚙️ Building: Loan Prediction API
  • 🎯 Goal: Deploy on AWS Lambda

Journey

My development as an engineer focuses on transitioning from mathematical concepts to production software execution.

Foundation (2024)

Established foundational scripting in Python, learning data processing libraries (Pandas, NumPy) and basic statistical classification methods.

Machine Learning (2025)

Learned scikit-learn pipeline engineering to prevent training-serving data leakage. Began exploring REST API architectures using FastAPI.

Systems Engineering (2026)

Started a QA Internship at Panacee, translating validation concepts into structured test scripts. Currently learning Terraform configurations for serverless deployment environments.

3rd Year

NIMS B.Tech AIML

Core Tech Stack

Python Pandas NumPy scikit-learn OpenCV FastAPI Pydantic AWS (S3) Git

Case Studies

Interactive breakdowns of machine learning systems. Click on a case study header to expand detailed technical notes.

Loan Approval Prediction System

Explore Source →
Python Pandas scikit-learn FastAPI Pydantic

01. Overview

A classification model and API designed to predict loan approval outcomes using applicant financial profiles.

02. Problem

Manual credit evaluation is slow and subjective. Automating classifications requires preprocessing numeric/categorical features and exposing predictions as a fast, type-safe API.

03. Approach

Created an end-to-end preprocessing and model pipeline with scikit-learn, validating inputs using Pydantic, and serving inference requests via a FastAPI web server.

04. System Design

Client Request (JSON) │ ▼ FastAPI Gateway │ ▼ Pydantic Validation (Type Verification) │ ▼ scikit-learn Pipeline (Scaling/Encoding) │ ▼ Tabular Classifier Model │ ▼ JSON Classification Response

05. Engineering Decisions

Selected scikit-learn for training to leverage its native Pipeline interface. Chose Pydantic schema validation inside FastAPI to reject invalid client inputs at the API entry point.

06. Challenges

Data leakage between folds occurred during separate categorical and numerical preprocessing. Solved by encapsulation inside unified ColumnTransformer and Pipeline flows.

07. Lessons Learned

Biggest Lesson (Model vs. System): Model accuracy wasn't the hardest problem. Building a reliable preprocessing pipeline and validating inputs correctly took significantly more engineering effort than training the model itself.

08. Future Improvements

Provisioning the FastAPI microservice to deploy automatically on AWS Lambda serverless endpoints using Terraform configurations.

09. Live Demo

Not available (Local REST prediction API only).

Engineering Journal

Learning in public: technical documentation logs detailing ML workflows, code investigations, and system architectures.

scikit-learn July 2026

Learning scikit-learn Pipelines

Documenting how to construct formal ML preprocessing pipelines. Bundling scaling, imputers, and encoders inside Pipeline and ColumnTransformer modules to enforce validation rules and prevent data leakage during training splits.

API Design July 2026

Understanding FastAPI and Pydantic validation

Building HTTP REST APIs for local model inference. Using FastAPI query endpoints and declaring Pydantic base schemas to validate input json data payloads, generating clean self-documenting OpenAPI endpoints automatically.

Cloud July 2026

Deploying AWS Lambda with Terraform

Investigating Infrastructure as Code (IaC) architectures. Writing basic Terraform scripts to define and automate AWS Lambda serverless functions, testing endpoints deployment and IAM permissions roles configuration.

Learning Roadmap

A structured summary of my immediate focus and technical progression path.

Currently Exploring

  • • Python programming
  • • Tabular datasets (Pandas, NumPy)
  • • scikit-learn modeling
  • • FastAPI & Pydantic validation
  • • Git version control

Next

  • • Terraform configurations
  • • Containerization concepts
  • • AWS Lambda setup

Future

  • • AWS API Gateway setup
  • • Basic CI/CD scripts
  • • Data validation checks

Long-term

  • • Model registries & tracking
  • • Automated monitoring
  • • Data versioning systems

Let's Build Something Together

Let's Connect!

I'm always interested in discussing machine learning systems, software engineering, internships, and collaborative projects. Feel free to reach out through the contact form or connect with me directly.

Phone

+91 8797599640

Location

New Delhi, India