Skip to content
View Adamkhald's full-sized avatar

Highlights

  • Pro

Block or report Adamkhald

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
Adamkhald/README.md

Adam Khald

AI & Data Science Engineer · Researcher in Explainable AI, Multi-Agent Systems & Autonomous Perception


About Me

I am a final-year AI & Data Science Engineering student at ENSAM Meknès, Université Moulay Ismaïl (Morocco), graduating June 2027. My work sits at the intersection of explainable AI, multi-agent LLM systems, and autonomous perception — with a common thread of making complex, multi-stage AI pipelines transparent and auditable rather than treating them as black boxes.

Alongside research, I have spent the last two years building and shipping production AI systems across fintech, healthcare imaging, and applied machine learning tooling, giving me hands-on experience with the practical failure modes that motivate my research questions.

  • Currently completing a vehicle trajectory prediction study (PointNet + BiLSTM with attention) on nuScenes
  • Background spans applied ML (computer vision, time-series, NLP) and production AI systems engineering across three internships and one independent AI agent platform
  • Open to research collaborations and co-authorship

Research Interests

Explainable AI (XAI) Causal and structural explanation methods for opaque, multi-stage AI pipelines.

Multi-Agent Systems Coordination, failure modes, and interpretability of hierarchical LLM-based agent architectures.

Autonomous Systems & Perception Trajectory prediction and spatiotemporal modeling for autonomous vehicles.

Deep Learning Architectures combining geometric representations (point clouds) with sequential modeling for structured prediction tasks.


Research Publications

Hierarchical Explanation Graph (HEG): Causal Explainability for Hierarchical LLM Multi-Agent Pipelines

Abstract / Contribution: HEG introduces a causal explainability framework for hierarchical, multi-agent LLM pipelines — systems where multiple orchestrators, planners, and executors interact across layers, making failure attribution notoriously difficult. A dual-orchestrator architecture executes the pipeline normally while a parallel orchestrator perturbs each layer's intermediate state and measures the resulting shift in the final output via cosine divergence, producing an experimentally grounded causal weight per layer. Across 7 tasks and 42 perturbation experiments, the framework detects systematic confabulation — self-explanations that are causally disconnected from the layer's actual influence on the output — most notably in the final evaluator layer, which explains its output with full confidence despite having near-zero measured causal contribution.

This work is positioned at the intersection of interpretability research and practical multi-agent system reliability, providing a diagnostic tool for auditing complex agentic AI systems rather than trusting their self-reports.

DOI: 10.5281/zenodo.21009192 Affiliation: ENSAM Meknès Status: Published on Zenodo; arXiv submission in preparation

In progress: Vehicle Trajectory Prediction (PointNet + BiLSTM with Attention, nuScenes)

A trajectory prediction model combining point-cloud feature extraction (PointNet) with a BiLSTM-Attention sequence model, benchmarked on the nuScenes dataset. Builds on prior CARLA-simulation-based autonomous vehicle work. Full research pipeline set up (EDA, baseline benchmarking, model implementation, ablations, writeup). Manuscript in preparation.


Featured Projects

🔹 Hierarchical Explanation Graph (HEG)

Causal explainability framework for hierarchical multi-agent LLM pipelines, detecting confabulated self-explanations via controlled perturbation experiments. Tech: Python, GPT-4o, dual-orchestrator architecture · Status: Published (Zenodo), arXiv in prep

🔹 Ciffeer

AI agent SaaS platform designed and built solo (Corarea). Multi-layer planning architecture (Orchestrator → Planner → Mid-Level Planner → Analyser → Executor → Evaluator), 100+ tools across 15 categories, semantic memory via pgvector. Tech: Go, Python/FastAPI, Next.js, Supabase/pgvector, GCP Cloud Run · Status: Live in production

🔹 COLFI Back-Office Platform & LLM Monitoring Agent

React + FastAPI back-office platform for corporate action processing and treasury funding allocation. Built an LLM monitoring agent on top of the existing multi-agent orchestration system for financial model drift detection (PPCA-based) and governed alerting. Tech: React, FastAPI, PostgreSQL, OpenAI API, multi-agent orchestration · Status: Private repository

🔹 ColFi Collateral Finance Management DApp

Decentralized collateral/asset management platform for financial institutions. Hyperledger Fabric chaincode for asset state transitions and audit trails, Next.js frontend, Fabric network hosted on Amazon EC2. Tech: Hyperledger Fabric, Next.js/TypeScript, AWS EC2, AWS Amplify · Status: Public repository Repository

🔹 Insight-Ray

AI-powered chest X-ray analysis system detecting 14 thoracic abnormality classes with YOLOv8, fine-tuned on VinBigData (18,000+ images), with Gemini-generated natural-language explanations of findings. Research/educational tool, not for clinical use. Tech: YOLOv8/Ultralytics, Flask, Tkinter, Gemini API · Status: Public repository Repository

🔹 Dalil AI

Offline-first desktop research platform unifying scikit-learn, PyTorch, TensorFlow, MediaPipe, and Stable-Baselines3/Gymnasium behind one GUI — classical ML, deep learning, computer vision, and RL, all local, no cloud dependency. Tech: Python, PyTorch, TensorFlow, scikit-learn, MediaPipe · Status: Public repository Repository · Website

🔹 Breiman CART

Pure Python, from-scratch reimplementation of the original CART algorithm (Breiman, Friedman, Olshen & Stone, 1984), with cost-complexity pruning, native categorical feature handling, and full tree inspection. Tech: Python · Status: Published on PyPI PyPI · Repository


Industry & Applied Experience

COLFI — London-based fintech · DApp Developer Intern, Summer 2025 Built the Hyperledger Fabric-based collateral management DApp described above.

COLFI — London-based fintech · Second internship Contributed the LLM-based financial model monitoring agent described above, built on the platform's existing multi-agent orchestration system.

OCP MEA — Integrated Mine, MEA washing facility · Internship Proposed a machine-learning-based soft sensor for pulp density estimation, scoped and delivered over a three-week engagement.


Awards & Recognition

  • 1st Prize, Innov'am 2024 — Autonomous TGV bogie inspection robot
  • 3rd Prize, Innovathon 2024

Technical Skills

Languages: English, French, Arabic, German (B2, self-studied)


Currently Learning

Expand
  • Advanced causal inference methods for AI interpretability
  • Geometric deep learning for 3D perception
  • Formal approaches to multi-agent system verification

Connect with Me


"The purpose of research is not to eliminate uncertainty, but to make it legible enough to act on."

Pinned Loading

  1. breiman-cart breiman-cart Public

    Implementation of Breiman's CART (Classification and Regression Trees) algorithm

    Python 1

  2. HEG-A-Causal-Framework-for-Explainability-in-Hierarchical-LLM-Based-Multi-Agent-Systems HEG-A-Causal-Framework-for-Explainability-in-Hierarchical-LLM-Based-Multi-Agent-Systems Public

    I introduce the Hierarchical Explanation Graph (HEG), a two-level framework that distinguishes self-reported explanations from experimentally derived causal explanations. Using dual orchestrators a…

    Jupyter Notebook 1

  3. colfi-internship-dapp colfi-internship-dapp Public

    This project is a blockchain-based web application developed during my internship at Colfi, focused on investing and collateral management.

    TypeScript

  4. InsightRay InsightRay Public

    Insight Ray is a desktop application designed to assist doctors by quickly analyzing medical images using artificial intelligence. It allows users to import images and use an AI model to classify t…

    Jupyter Notebook