Adam Khald — Research Portfolio — 2026

Adam
Khald

AI & Data Science Engineer.

Adam Khald
FieldExplainable AI · Multi-Agent Systems · Autonomous Perception
Based inMeknès, Morocco
StatusFinal-year engineering, graduating June 2027
§01About

Final-year AI & Data Science Engineering student at ENSAM Meknès, Université Moulay Ismaïl (Morocco), graduating June 2027. Specializing in AI and Data Science applied to industrial systems.

Research Focus

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.

Applied Practice

Alongside research, spent the last two years building and shipping production AI systems across fintech, healthcare imaging, and applied machine learning tooling.

Background

Applied ML spanning computer vision, time-series, and NLP, plus production AI systems engineering across three internships and one independent AI agent platform.

§02Research Publications
Zenodo ENSAM Meknès

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

Published on Zenodo · arXiv submission in preparation
Abstract

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.

§03Featured Projects
01Published

Hierarchical Explanation Graph (HEG)

Causal explainability framework for hierarchical multi-agent LLM pipelines, detecting confabulated self-explanations via controlled perturbation experiments.

Python · GPT-4o · Dual-Orchestrator Architecture
02Live

Ciffeer

AI agent SaaS platform designed and built solo, under own entity (Corarea). Multi-layer planning architecture — Orchestrator → Planner → Mid-Level Planner → Analyser → Executor → Evaluator. 100+ tools across 15 categories, DeepSeek as LLM backbone, semantic memory via pgvector, deployed on Google Cloud Run.

Go · Python/FastAPI · Next.js · Supabase/pgvector · Docker · GCP Cloud Run
03Private Repo

COLFI Back-Office Platform & LLM Monitoring Agent

React + FastAPI back-office platform for corporate action processing, OCR-assisted document extraction, ISO 20022 payload generation, and treasury funding allocation optimization. Contribution centered on an LLM monitoring agent for detecting and narrating drift in financial models — PPCA-based drift detection, a deterministic cash placement optimizer, and a governed recommendation schema.

React · FastAPI · PostgreSQL · OpenAI API · Multi-Agent Orchestration
04Public Repo

ColFi Collateral Finance Management DApp

Decentralized asset and collateral management platform for financial institutions. Hyperledger Fabric chaincode for asset state transitions, collateral locking/unlocking, and immutable audit trails, with a Next.js frontend and a Fabric network hosted directly on Amazon EC2, backend via AWS Amplify.

Hyperledger Fabric · Next.js/TypeScript · AWS EC2 · AWS Amplify
05Public Repo

Insight-Ray

AI-powered chest X-ray analysis system detecting and classifying 14 thoracic abnormality classes using a YOLOv8 model fine-tuned on the VinBigData Chest X-ray Abnormalities Detection dataset (18,000+ images). Combines detection with natural-language explanations via Google's Gemini API. Research/educational tool, not for clinical use.

YOLOv8/Ultralytics · Flask · Tkinter · Gemini API
06Public Repo

Dalil AI

Offline-first desktop research platform unifying scikit-learn, PyTorch, TensorFlow, MediaPipe, and Stable-Baselines3/Gymnasium behind a single GUI. 7-step scikit-learn wizard, PyTorch transfer-learning lab, TFLite export for edge deployment, real-time MediaPipe vision, and an RL Studio for training PPO/DQN/SAC agents.

Python · PyTorch · TensorFlow · scikit-learn · MediaPipe
07PyPI

Breiman CART

Pure Python, from-scratch reimplementation of the original CART algorithm as specified by Breiman, Friedman, Olshen, and Stone (1984) — cost-complexity pruning, native categorical feature handling, and full tree inspection. Published as an installable package.

Python
08In Progress

Vehicle Trajectory Prediction

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. Manuscript in preparation.

PointNet · BiLSTM · Attention · nuScenes
§04Industry & Applied Experience
Summer 2025

DApp Developer Intern

COLFI — London-based fintech

Built a decentralized asset and collateral management platform on Hyperledger Fabric. Chaincode for asset state transitions, collateral locking/unlocking, and immutable audit trails, with a Next.js frontend and a Fabric network hosted directly on Amazon EC2, backend via AWS Amplify (API Gateway, Lambda, DynamoDB).

Second Internship

LLM Monitoring Agent

COLFI — London-based fintech

Contributed an LLM-based financial model monitoring agent, built on top of the platform's existing multi-agent orchestration system, for detecting and narrating drift in financial models — including PPCA-based drift detection, a deterministic cash placement optimizer, and a governed recommendation schema.

§05 Awards & Recognition
Innov'am 2024 1st Prize — Autonomous TGV Bogie Inspection Robot

Winner with Siana for developing an autonomous robotic system for high-speed train bogie inspection.

Innovathon 2024 3rd Prize

Awarded at the Fès-Meknès Economic Forum Hackathon for developing Ciffeer, an AI multi-agent platform.

§06Technical Skills
Python
C++
Go
PyTorch
TensorFlow
OpenCV
scikit-learn
NumPy
Pandas
FastAPI
Next.js
Docker
Git
Linux
Google Cloud
AWS
SQL
English French Arabic German — B2, self-studied
>_ terminal
adam@portfolio — bash
Type a path to jump to a section, e.g. Adam's portfolio > Featured_projects
Sections: about · publications · projects · experience · awards · skills · contact — or type help
guest@adam:~$