Skip to content
View hammadkhann's full-sized avatar
:electron:
:electron:
60 followers · 185 following

Achievements

Achievement: Starstruck

Achievements

Achievement: Starstruck

Block or report hammadkhann

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
hammadkhann/README.md

Typing SVG

Machine Learning Scientist at Expedia Group
Previously Flo Health · Cookpad · Alibaba Group · Huawei · MSc Data Science, University of Glasgow

LinkedIn X Substack Medium

About

Building AI-powered travel experiences at Expedia — from property search and recommendations to agentic assistants that understand traveler intent. I spend my time on LLM evaluation, agent orchestration, and making ML systems that work reliably at scale.

Domains

Search & Ranking Recommendation Systems LLMs & Agents NLP Information Retrieval

Approach

Learned Retrieval Semantic Search Deep CTR RAG Pipelines Agent Evaluation Personalization

Writing

Agentic Engineering: What Actually Works After Hundreds of Sessions

Workflows, patterns, and hard-won lessons from building production software with AI coding agents. Plan mode, de-slop passes, fighting "sneaky quokka" behavior, and why you're the architect — not the builder.

Claude Code Codex Cursor AI Agents Python

More writing on Substack and Medium

Tech

Open Source

dotfiles
Portable config for Claude Code, Codex CLI, Cursor, Fish, and Ghostty — 100+ files, custom hooks, 60+ slash commands, prompt injection defender

LLM-Experiments
Experiments with large language models — retrieval, evaluation, and prompting techniques

Effective CLS Token for ColBERT
Research on reducing ColBERT's storage cost through CLS token representations

Boolean Retrieval Model
Inverted index and positional index implementation for Boolean information retrieval

ego = 1 / knowledge

Pinned Loading

  1. pyterrier_colbert pyterrier_colbert Public

    Forked from terrierteam/pyterrier_colbert

    Jupyter Notebook

  2. ColBERT ColBERT Public

    Forked from stanford-futuredata/ColBERT

    ColBERT: Contextualized Late Interaction over BERT (SIGIR'20)

    Python

  3. State-based-LWW-Element-Graph State-based-LWW-Element-Graph Public

    This repository implements state-based LWW-Element-Graph CRDT in python.

    Python 1

  4. Effective-CLS-Token-Representation-for-ColBERT-A-Step-Towards-Reducing-the-Storage-Cost Effective-CLS-Token-Representation-for-ColBERT-A-Step-Towards-Reducing-the-Storage-Cost Public

    Jupyter Notebook

  5. Boolean-Retrieval-Model Boolean-Retrieval-Model Public

    The objective of this assignment is to make you understand how different indexes work in retrieving different query from a collection. You will create Inverted index and positional index for a set …

    Python 2 2

  6. ML-for-AI-and-DS ML-for-AI-and-DS Public

    Machine Learning for AI and DS Case Studies.

    Jupyter Notebook