---
title: "Farhan Naqvi (@farhan16) | Hashnode"
description: "MSc Computer Science @ University of Stuttgart | Ex-Cohesity | Ex-Veritas | Open to SWE / ML Engineering Roles in Europe"
url: "https://hashnode.com/@farhan16"
---

@farhan16

# Farhan Naqvi

@farhan16 · Stuttgart, Germany · Joined March 2024

MSc Computer Science @ University of Stuttgart | Ex-Cohesity | Ex-Veritas | Open to SWE / ML Engineering Roles in Europe

### [Building a Visual Workflow Designer for LLM Multi-Agent Systems](https://farhanbytemaster.hashnode.dev/building-a-visual-workflow-designer-for-llm-multi-agent-systems?utm_source=hashnode&utm_medium=feed)

This project is a prototype that brings together visual workflow composition, agent orchestration, retrieval-augmented generation (RAG), and runtime inspection in a single experience.

4 min read · [farhanbytemaster.hashnode.dev](https://farhanbytemaster.hashnode.dev/building-a-visual-workflow-designer-for-llm-multi-agent-systems?utm_source=hashnode&utm_medium=feed)

[Jun 15](https://hashnode.com/posts/building-a-visual-workflow-designer-for-llm-multi-agent-systems/6a2f5717481a13f30b61091e)

### [Building a Distributed Storage Metadata Service in Go](https://farhanbytemaster.hashnode.dev/building-a-distributed-storage-metadata-service-in-go?utm_source=hashnode&utm_medium=feed)

A Deep Dive into Chunk-Based Deduplication, gRPC Streaming, and Garbage Collection

6 min read · [farhanbytemaster.hashnode.dev](https://farhanbytemaster.hashnode.dev/building-a-distributed-storage-metadata-service-in-go?utm_source=hashnode&utm_medium=feed)

[Jun 13](https://hashnode.com/posts/building-a-distributed-storage-metadata-service-in-go/6a2dd42f83a0b75ab845ad48)

### [How are tokens processed by ML models?](https://farhanbytemaster.hashnode.dev/how-are-tokens-processed-by-ml-models?utm_source=hashnode&utm_medium=feed)

After you perform tokenization, the numerical identifiers representing each token are typically converted into embeddings before being processed by ML models. Embeddings are dense, lower-dimensional vector representations of tokens that capture seman...

2 min read · [farhanbytemaster.hashnode.dev](https://farhanbytemaster.hashnode.dev/how-are-tokens-processed-by-ml-models?utm_source=hashnode&utm_medium=feed)

[Apr 28, 2024](https://hashnode.com/posts/how-are-tokens-processed-by-ml-models/662e964e71272644a5a4b0e7)

### [What are special tokens in Tokenization?](https://farhanbytemaster.hashnode.dev/what-are-special-tokens-in-tokenization?utm_source=hashnode&utm_medium=feed)

Special tokens are additional tokens added during the tokenization process to serve specific purposes in natural language processing tasks. These tokens are not derived from the original text but are inserted to provide additional information or perf...

3 min read · [farhanbytemaster.hashnode.dev](https://farhanbytemaster.hashnode.dev/what-are-special-tokens-in-tokenization?utm_source=hashnode&utm_medium=feed)

[Apr 17, 2024](https://hashnode.com/posts/what-are-special-tokens-in-tokenization/661f558f2cea5d8a6be898e4)

### [What is Tokenization?](https://farhanbytemaster.hashnode.dev/what-is-tokenization?utm_source=hashnode&utm_medium=feed)

Tokenization is the process of breaking down a sequence of text into smaller units, called "tokens". These tokens could be words, subwords, characters, or even phrases, depending on the specific tokenization strategy used. Tokenization is a fundament...

4 min read · [farhanbytemaster.hashnode.dev](https://farhanbytemaster.hashnode.dev/what-is-tokenization?utm_source=hashnode&utm_medium=feed)

[Apr 15, 2024](https://hashnode.com/posts/what-is-tokenization/661cae9245f8a7f5dff4c75a)
