Skip to content

Chamel Nadir Bouacha

AI researcher and software engineer

I work on retrieval and representation learning that preserve when things were true, especially in longitudinal healthcare data.

Get in touch

Latest distinction 1st place · DataHack Datathon, 3rd Edition Feb. 2026

  • Research collaboration, Télécom SudParisJune 2026 – present
  • Junior Full-Stack Developer, Momentum WorldwideJuly 2026 – present

As of September 2026Developing TempMedBench, a synthetic patient-timeline retrieval benchmark and generation pipeline.

Portrait of Chamel Nadir Bouacha
  1. 2021 ESI
  2. 2024 NYUAD
  3. 2025 Maystro Delivery
  4. 2025 Télécom SudParis
  5. 2025 Samsung Innovation Campus
  6. 2026 Télécom SudParis
  7. 2026 Momentum Worldwide

Selected work

01in development

TempMedBench

A synthetic patient-timeline retrieval benchmark and generation pipeline for temporally faithful healthcare retrieval and reasoning.

Explore project

02completed

Temporal RAG for Healthcare

A retrieval-first architecture that combines semantic relevance with explicit temporal constraints over longitudinal healthcare information, addressing temporal granularity, event-time anchoring, provenance, and retrieval-time consistency.

Explore project

03Feb. 2025 – June 2025

IRCHAD — Indoor Navigation for the Visually Impaired

Explore project

Engineering

I build the systems my research needs and apply the same engineering discipline at work.

  • July 2026 – present · Momentum Worldwide

    Python/FastMCP server

    Built and deployed a Python/FastMCP server converting existing repository business logic and skills into MCP tools, resources, and prompts, so every Momentum employee who uses Claude can use them from claude.ai.

  • July 2025 – Oct. 2025 · Maystro Delivery

    Moriarty — multi-agent analytics pipeline

    Architected and deployed a modular multi-agent analytics pipeline on GCP Cloud Run that processed scheduled Google Analytics data into behavioural reports and UI/UX recommendations, with CI/CD through Cloud Build.

    One of three interns: set up the multi-agent codebase, built the report generator (HTML, JSON and PDF reports) and the Next.js dashboard, contributed to behaviour analysis and session-cluster labelling, and took the system to production on Google Cloud.

  • July 2024 – Oct. 2024 · New York University Abu Dhabi (NYUAD)

    Automatic Code Optimization

    Built a pipeline that converts PyTorch models into MLIR intermediate representations using the Linalg and TOSA dialects.

    Solo: found and packaged a working path from PyTorch to MLIR through torch-mlir's FX importer, for NLP models and other simpler models.

Research

Relevant is not always valid.

The Télécom SudParis internship introduced me to temporal RAG for healthcare. While surveying the field for my Master’s review thesis, I became interested in a problem: retrieved evidence can be semantically relevant yet wrong in time. Building the system for my State Engineer thesis made that problem concrete. TempMedBench grew from that work as a way to evaluate it.

One time axis. Evidence A, “[medication] started”, is valid from t1 to t2. Evidence B, “[medication] stopped”, is valid from t2 onward.

Fig. 1 Both records are relevant to the question; only B is valid when it is asked (tq). Illustrative; synthetic.

All research

Papers & theses