Data & AI Architect · Île-de-France

Designing AI agents for regulated environments

From MCP and A2A protocol design at Crédit Agricole to production text-to-SQL, vehicle-diagnostics, and fraud-detection systems — pairing experimentation with governance so analysts, technicians, and legal teams trust every output.

MCP + A2A protocol design at enterprise scale
Multi-agent reasoning over vehicle telemetry
Text-to-SQL copilots for finance leadership
Reproducible benchmarks before adopting frameworks

Focus Areas

Each partnership blends data science, AI integration, and production-grade craftsmanship. I help teams move from proof of concept to trusted production systems with responsible AI practices embedded throughout.

Production-grade AI Operations illustration

Production-grade AI Operations

Designing repeatable pipelines with observability, automated evaluations, and compliance built in from day zero.

LLM Integration illustration

LLM Integration

Embedding retrieval-augmented generation, semantic parsers, and copilots that accelerate expert workflows without sacrificing trust.

Multi-Agent Architecture illustration

Multi-Agent Architecture

Designing MCP and A2A protocol patterns that let specialised agents coordinate safely — with tool permissions, audit trails, and the freedom to swap LLM backends.

Capability surface · living map

Four disciplines, one delivery rhythm

Nodes drift. Drag any skill to rearrange the constellation. Hover to read every mission where it shipped.

JBARCHITECTMCPA2A ProtocolMulti-agentLangChainRAGText-to-SQLAWS BedrockAWS SageMakerAWS LambdaTerraformAWS CDKMLflowGitLab CI/CDZenML · DVCOpenSearchPythonXGBoostRandom ForestLSTMTensorFlowspaCy · GensimWord2Vec · LDAPySparkHadoopNeo4j · CypherQLSQLDatabricksVector DBsLLMEXPERTMLOpsEXPERTML7YDataSENIOR
28 skills · live
Experience

Shipped inside regulated environments

  1. Finance

    Data & AI Architect

    Crédit Agricole Technologies and Services (Reply)

    Nov 2025 — Present

    Focus

    MCP + A2A

    Env.

    Enterprise banking

    Scope

    Architecture

    • Architecting Model Context Protocol (MCP) design patterns enabling seamless AI agent orchestration across distributed banking systems.
    • Driving proof-of-concept implementations for the Agent-to-Agent (A2A) protocol, establishing communication standards for autonomous service coordination.
    • Delivering technical blueprints for scalable AI infrastructure supporting compliance-first financial services environments.
    PythonMCPA2AMulti-AgentLLMAWS
  2. Finance

    AI / LLM Engineer

    Stellantis Financial Services (Reply)

    Mar 2025 — Oct 2025

    Query accuracy

    85.6%

    Analysts empowered

    40+

    Decision cycle

    −27%

    • Architected a Text-to-SQL system enabling 40+ financial analysts to query complex financial databases in natural language — removing the IT-team bottleneck.
    • Semantic parsing + query optimization hit 85.6% accuracy and cut average response time from minutes to under 20 seconds.
    • Built an evaluation framework on accuracy, latency, and user satisfaction; decision-making cycle reduced by 27% thanks to faster insights.
    • Delivered production-ready AWS pipelines with scalability and financial-services compliance baked in.
    PythonAWS LambdaLangChainOpenSearchRAGAWS Bedrock
  3. Mobility

    Machine Learning Engineer

    Stellantis R&D (Reply)

    Feb 2025 — Jun 2025

    Anomaly accuracy

    72.8%

    Diagnostic time

    −24.5%

    Warranty savings

    €1.1M/yr

    • Designed an LLM-powered diagnostic system analyzing connected-vehicle sensor streams to detect and explain anomalies in natural language.
    • Shipped a knowledge-retrieval pipeline linking anomalies to troubleshooting docs and repair procedures, with a root-cause layer translating sensor data into actionable repair insights.
    • Achieved 72.8% anomaly detection accuracy, reduced diagnostic time by 24.5%, cut misdiagnosis by 14.2% — estimated €1.1M/year saved in warranty claims.
    PythonAWS SageMakerAWS BedrockVector DBsRAGAWS CDK
  4. Mobility

    Machine Learning Engineer

    SNCF (Talan)

    Sep 2024 — Dec 2024

    Fraud rate

    7.2 → 5.9%

    AUC-ROC

    >0.87

    Volume RMSE

    14.7%

    • Inside TER's data squad, brought ticketing fraud rate from 7.2% → 5.9% through hypothesis testing and optimized controls.
    • Developed predictive models (RF, XGBoost, LSTM) with exogenous variables, achieving AUC-ROC > 0.87.
    • Regression models forecast fraud volumes at 14.7% RMSE, enabling smarter inspector resource allocation.
    Random ForestXGBoostLSTMPython
  5. Energy

    Machine Learning Engineer

    GRTgaz (Talan)

    Jun 2023 — Aug 2024

    Support time

    −38.5%

    Program

    R&D innovation

    Practice

    TDD adopted

    • Gas Propagation Tool: built predictive time-series models for pipeline gas dynamics, improving incident anticipation across France's gas transport network.
    • LLM Chatbot: led development of a Confluence-integrated assistant — reduced support response times by 38.5%.
    • Introduced TDD and continuous retraining discipline across the team, materially improving maintainability.
    PythonAWS SageMakerAWS BedrockAWS LambdaOpenSearch
  6. Legaltech

    Machine Learning Engineer

    LexisNexis (Devoteam)

    Sep 2022 — Jun 2023

    Deployment cycles

    −41%

    Squad

    MLOps · 3

    Scope

    Global scale

    • Stood up a full MLOps platform — deployment cycles down 41%, release reliability materially improved.
    • Refactored Python codebases to cut tech debt and built CI/CD pipelines (GitLab, ZenML, MLflow, DVC) for automated ML workflows.
    • Managed AWS infrastructure with Terraform (incl. SageMaker) for scalable deployment of ML products used by thousands of legal professionals.
    PythonAWSTerraformGitLabZenMLDVCMLflow
  7. Finance

    Data Engineer

    Generali (CGI)

    Jul 2021 — Jul 2022

    Manual workload

    −24%

    Scale

    Millions of txns

    Domain

    AML/CTF

    • Implemented an AML/CTF fraud detection system, improving compliance posture and reducing false negatives.
    • Built PySpark/Hadoop pipelines lifting data quality across millions of transactions; automated workflows cut manual workload by 24%.
    • Leveraged Neo4j (CypherQL) to detect fraud networks and suspicious relational patterns.
    PythonPySparkHadoopNeo4jCypherQL
  8. Finance

    Data Scientist

    BPI France · AG2R La Mondiale (CGI)

    Mar 2021 — Jun 2021

    Processing time

    −34%

    F1-score

    +11.8%

    Focus

    OCR + NLP

    • Built ML/DL models for OCR of printed and handwritten text, cutting manual processing time by 34%.
    • Hyperparameter tuning lifted prediction accuracy by +11.8% F1-score; ran text-similarity analysis for document classification and deduplication.
    PythonTensorFlow
  9. Public sector

    Data Scientist

    DGFiP (CGI)

    Oct 2018 — Jun 2019

    Ministry

    Finance

    Scope

    Citizen services

    Focus

    NLP automation

    • Built NLP models for text classification, topic modeling, and chatbots supporting modernization of citizen-facing digital services.
    • Automated information-extraction pipelines and deployed Flask web apps + scraping pipelines in production.
    PythonFlaskNLTKWord2VecLDAspaCyGensim
Writing

Field notes on shipping AI

View All Articles →

Recommendations

Testimonials from colleagues, managers, and clients who have worked with me on AI projects across various industries.

AA

Amine AIT EL HARRAJ

Driving Cloud & AI Innovation

Ex-AWS | SaaS Co-Founder

Managed Jaafar directlyJuly 28, 2025
I had the pleasure of working with Jaafar on two key AI projects at Stellantis Financial Services: text-to-SQL automation and IoT anomaly detection using LLMs. He consistently brought deep technical expertise, especially in NLP and large language models, paired with a strong understanding of business needs. Jaafar stands out for his ability to simplify complex ideas, build scalable solutions, and collaborate effectively across teams. I highly recommend him for any AI or data science role—he's a rare blend of technical depth and practical insight.
NH

Nicolas Hartmann

Solution Architect

Stellantis

Managed Jaafar directlyJuly 15, 2025
I had the pleasure of working with Jaafar on an interactive POC exploring a RAG-based architecture for SQL generation from natural language (TXT2SQL). Jaafar demonstrated great autonomy, strong technical insight, and quickly adapted to the complex and highly technical banking environment. His communication skills, the quality of the testing, results, and documentation were all highly appreciated. A valuable contributor I would gladly recommend.
HJ

Hamza Jalouaja

AI Engineer

AI Operations | AI Architect

Senior colleague at GRTgazDecember 23, 2024
I had the opportunity to work with Jaafar at GRTgaz, where he contributed to several projects. Jaafar is a serious and involved person, with a real will to learn and progress. He integrates well into a team and has shown that he can be an asset in a well-structured and organized environment.
DC

David Cabellan

Expert Big Data / Lead Tech

SNCF Client

Client on fraud detection projectDecember 2, 2024
I worked with Mr. BENABDERRAZAK on a POC for fraud prediction at TER for all trains. He was proactive, persevering, driving in choosing external sources, and very professional. He provided us with very methodical documentation describing his hypotheses and choices, as well as numerous explanatory diagrams. We discussed various algorithms, errors, sources, methods, and I appreciated challenging each other to achieve a better result. The cherry on top is his relationship with others, his good communication, and very good exchanges with clients, teams, and experts. In summary, Mr. BENABDERRAZAK is a good professional in his field and a good communicator whom I highly recommend.
CL

Corentin Leloup

Data Scientist

Quantmetry

Worked on the same teamMarch 26, 2023
I worked with Jaafar for a year. His expertise in data science and AI engineering is remarkable. He is professional, passionate about his work, and has in-depth knowledge of emerging technologies. He knows how to adopt an innovative approach to solve complex problems. He is genuinely interested in this field and therefore always knows the latest innovations, which he sometimes explores through personal projects.

Certifications & Credentials

Professional certifications demonstrating expertise in machine learning, cloud architecture, and AI technologies from industry-leading organizations.

Data Engineering

AWS Certified Data Engineer – Associate

Amazon Web Services (AWS)

Issued Dec 2024
Hugging Face logo
AI

AI Agents Fundamentals

Hugging Face

Issued Sep 2025

Credential ID: jbenabde

Amazon Web Services (AWS) logo
ML

AWS Certified AI Practitioner

Amazon Web Services (AWS)

Issued Feb 2023
Amazon Web Services (AWS) logo
Cloud

AWS Certified Cloud Practitioner

Amazon Web Services (AWS)

Issued Jan 2023
Amazon Web Services (AWS) logo
Architecture

AWS Certified Solutions Architect – Associate

Amazon Web Services (AWS)

Issued Jan 2023
Dataiku logo
Data Science

Dataiku Core Designer

Dataiku

Issued Jun 2022

Credential ID: xeizska962nr

National Research University — Higher School of Economics logo
NLP

Natural Language Processing

National Research University — Higher School of Economics

Issued Nov 2021
TensorFlow Certificate Program logo
Deep Learning

Google TensorFlow Developer Certificate

TensorFlow Certificate Program

Issued Nov 2020
Ready to collaborate

Let's design the next intelligent system

Whether you're validating an MVP, hardening an LLM copilot for production, or modernising analytics infrastructure, I bring a blend of experimentation, governance, and delivery discipline.

Find a time on Calendly

Reserve a slot that fits your schedule—the invite will include call details instantly.

Send a direct email

Drop a note about your challenge or opportunity and I'll respond within 24 hours.

AI copilot

Ask about Jaafar’s AI projects, articles, or experiments.