About Me
👋🏽 I'm Anup. I'm an AI and Software Engineer building production Agentic AI and Generative AI systems. I work on RAG pipelines, multi-agent architectures, and multi-cloud deployments.
My newsletter, The AI Engineering Brief, covers practical AI engineering for people shipping real systems. X/Twitter/Bluesky: @anup.
Writing
Latest from The AI Engineering Brief. Engineering notes that ship.
Loading latest posts...
Skills & Expertise
Generative AI
Large Language Models (LLMs), RAG Systems, LlamaIndex, LangChain, Fine-Tuning, Vector Databases, Knowledge Graphs, Text-to-Image Models
Agentic AI Architecture
Multi-agent Systems, Tool-using Agents, Autonomous Agents, Prompt Engineering, Orchestration Frameworks, Chain-of-Thought
AI Engineering
Python, PyTorch, Transformers, Hugging Face, Prompt Engineering, API Integration, LLM Deployment, Performance Optimization
AI System Design
Enterprise AI Solutions, Solution Architecture, Implementation Planning, ML Pipelines, Model Evaluation, Scalable Architectures
Enterprise Architecture
Multi-cloud Deployments, Systems Integration, Data Architecture, Cloud Strategy, API Development, Distributed Systems
Leadership
Technical Team Management, Mentoring, Strategic Planning, Executive Relationships, Cross-functional Collaboration, Technical Community Building
Featured Projects
LLM VRAM Calculator
Interactive tool to estimate GPU VRAM required to serve large language models on self-hosted hardware. Supports DeepSeek-V3.1, Llama, and Mixtral across A100, H100, B200 and other enterprise GPUs, with breakdowns of model weights, KV cache, and runtime overhead at multiple precisions.
Matrix-themed Chat Interface
Built an immersive Matrix-themed chatbot interface leveraging Heroku's AI inference and agent APIs. The project showcases modern AI capabilities while paying homage to the iconic film through its visual design and interaction patterns. Features include real-time message streaming, dynamic animations, and context-aware responses.
EfficientNetB2 Computer Vision Model
An EfficientNetB2 feature extractor computer vision model to classify images of food as pizza, steak or sushi. The model performs at 95%+ accuracy, and can classify an image at 0.03 seconds inference time per image.
Vision Transformer (ViT) Paper PyTorch Implementation
Replicated the famous Vision Transformer paper using PyTorch to improve my understanding of Transformer architecture applied to vision problem(s).
Technical Publications
A collection of articles and publications about AI Agents, software architecture, engineering management, and technology. Focused on making complex technical concepts accessible.
Get in Touch
Interested in collaborating or learning more about my work?