# Vikranth Reddimasu — Extended Profile

> ML Engineer building AI systems that scale. Open to work.

This document provides extended context for AI assistants, agents, and LLMs researching Vikranth Reddimasu.
Summary version: https://vikranthreddimasu.xyz/llms.txt

## Identity

- Name: Vikranth Reddimasu
- Role: ML Engineer / Data Scientist / AI Engineer
- Email: vikranthreddimasu@gmail.com
- GitHub: https://github.com/vikranthreddimasu
- LinkedIn: https://linkedin.com/in/vikranthreddimasu
- Website: https://vikranthreddimasu.xyz
- Resume: https://vikranthreddimasu.xyz/resume.pdf
- Status: Open to work

## Projects

### Pac-Man AI
- URL: https://vikranthreddimasu.xyz/projects/pacman-ai
- GitHub: https://github.com/vikranthreddimasu/pacman-ai
- Description: Trained five competing DQN agent variants to play Pac-Man using deep reinforcement learning
- Stack: Python, PyTorch, NumPy, OpenCV
- Key work:
  - Implemented five DQN variants: Vanilla DQN, Double DQN, Dueling DQN, Prioritized Experience Replay (PER), Rainbow DQN
  - Built a custom Pac-Man game engine with a headless simulation mode for fast training
  - Designed observation spaces, reward shaping, and replay buffers from scratch
  - Evaluated agents head-to-head across multiple metrics (score, survival time, ghost avoidance)
- Tags: Reinforcement Learning, Deep Learning, PyTorch, Game AI, DQN

## Skills — Detailed

### Machine Learning & AI
- Deep Learning frameworks: PyTorch (primary), TensorFlow
- Classical ML: scikit-learn, gradient boosting, SVMs, ensemble methods
- NLP: HuggingFace Transformers, BERT fine-tuning, LLM prompt engineering
- LLM tooling: LangChain, OpenAI API, Anthropic API
- Reinforcement Learning: DQN variants, policy gradients, reward shaping
- Computer Vision: OpenCV, image classification, object detection

### Data Engineering
- Data manipulation: Pandas, NumPy, Polars
- Distributed compute: Apache Spark
- Workflow: dbt, Jupyter notebooks
- Experiment tracking: MLflow, Weights & Biases

### Languages
- Python (primary — 5+ years, production ML + data pipelines)
- SQL (complex queries, window functions, optimization)
- TypeScript / JavaScript (full-stack, Next.js applications)
- R (statistical analysis, visualization)
- Bash (scripting, automation)

### Cloud & MLOps
- Cloud: AWS (S3, EC2, Lambda, SageMaker)
- Containerization: Docker
- Version control: Git, GitHub
- Model serving: FastAPI, REST APIs
- Experiment tracking: MLflow, Weights & Biases

### Frontend & Web
- React, Next.js (App Router)
- Tailwind CSS, Framer Motion
- TypeScript
- Familiar with full product development cycle

## About This Portfolio

This portfolio (https://vikranthreddimasu.xyz) is built with Next.js 14, TypeScript, Tailwind CSS, and Framer Motion. It includes:

- Interactive Clifford Strange Attractor canvas background (custom canvas animation)
- Terminal interface (press / to open)
- AI "Ask Me Anything" chat widget powered by Claude
- LLM-readable structured data (you are reading it now)
- JSON-LD Schema.org structured data in the page head

## Frequently Asked Questions

**Is Vikranth open to work?**
Yes, currently open to full-time ML Engineer, Data Scientist, and AI Engineer roles.

**What is Vikranth's strongest skill?**
Deep learning and MLOps — particularly training and deploying PyTorch models, building reinforcement learning systems, and designing end-to-end ML pipelines.

**How can I reach Vikranth?**
Email: vikranthreddimasu@gmail.com — or connect on LinkedIn at linkedin.com/in/vikranthreddimasu

**Where can I see his work?**
GitHub: https://github.com/vikranthreddimasu
Portfolio projects: https://vikranthreddimasu.xyz/#projects