// About — Mohamed Saadi

Closing the Gap Between
Research and Production.

Most AI initiatives stall not because the research is wrong — but because the gap between theoretical capability and a production-grade, observable, maintainable system is enormous. That gap is where I work.

My approach has never changed: identify which research advances will matter in practice, understand them at the mathematical level, then build the architecture and engineering culture that makes them work under real constraints — delivery timelines, legacy systems, regulated environments, and teams that weren't hired to run AI platforms.

"The rarest skill in AI is not knowing the research — it's knowing which research matters in production, and how to make it work for people who can't afford experiments."
10 years. 8 enterprise missions. One constant.

01 / Proven Enterprise Impact

EDF Group AI/ML Platform · AWS + OpenShift · 100+ daily training jobs · 10+ data science teams

Faster time-to-production

From ~6-week manual deployment cycles to 5-day automated pipelines. Achieved through standardized CI/CD, containerized model serving, and self-service tooling for data scientists.

30% Infrastructure cost reduction

On a multi-million euro AWS bill across a large industrial group. FinOps framework: right-sizing spot instances for training, reserved capacity for inference, automated idle resource cleanup.

99.9% Platform uptime SLA

Across 100+ daily training jobs and production inference services. Achieved with multi-AZ deployments, automated failover, Prometheus alerting, and zero-downtime deployment patterns.

60% Reduction in incident resolution time

From median 4h to under 90 minutes. Systematic observability (ELK, Evidently, Grafana), runbook automation, and on-call rotation across 3 timezone-aligned teams.

02 / On Environments

Depth Was the Point. Not the Limitation.

A legitimate question about a career with significant depth in one environment: does this translate elsewhere?

The answer is in the constraint profile. EDF is not one environment — it's three simultaneously: a regulated utility (compliance, auditability, no fast experiments), a large-scale legacy system integrator (Oracle, SAP, unmovable infrastructure), and an internal startup (the data division being built as a new capability inside a 150,000-person organization). Most difficult AI deployment scenarios are a subset of this combination.

For raw greenfield chaos: SeriesMind. Zero budget. No team. No infra. Solo architecture, product, and engineering decisions in parallel with a full-time mission. That context is as different from EDF as environments get.

And Sanofi: a GxP-adjacent pharmaceutical environment with its own validation requirements, documentation standards, and organizational culture. The ML engineering principles transferred. The execution approach had to be rebuilt from scratch.

03 / A Pattern, Repeated Three Times

Arriving Before the Market Has a Name for It.

Wave I — Data 2017–19

Research signal: Distributed computing, columnar storage, stream processing

Real-time 360° Customer View at EDF. Constraint: surrounding Oracle systems without replacing them.

Wave II — Cloud Native + MLOps 2019–21

Research signal: Reproducible pipelines, feature stores, model governance

Full MLOps stack built from scratch on AWS & OpenShift. Lesson: governance without team autonomy kills adoption.

Wave III — Agentic AI 2021–Now

Research signal: Multi-agent negotiation, neuro-symbolic reasoning, LLM orchestration

LangGraph, RAG, MCP at enterprise scale. The 2016 coordination theory — now stress-tested by production constraints theory never anticipated.

04 / On the 2016 Research

A Framework, Not a Trophy.

The LIP6 thesis on multi-agent negotiation is not mentioned as a credential. It's mentioned because it provides a precise vocabulary for evaluating current tools that most practitioners lack.

When I evaluate a LangGraph orchestration architecture, I'm asking the same questions I asked about JADE agents in 2016: what is the communication protocol? How is partial state handled? What are the failure modes when an agent receives contradictory information? How do you recover a multi-step workflow from a mid-execution fault?

The compute changed. The questions are identical. That theoretical grounding is why I can distinguish a framework that will hold in production from one that demos well.

2016 · École Nationale Polytechnique × LIP6 / CNRS Paris

A Multi-Agent Negotiation Approach for Supply Chain Management

188 pages · JADE · Nash Bargaining · AUML

05 / Experience Timeline

  1. 2015–16

    Research — Multi-Agent Systems

    LIP6 / CNRS Paris. Autonomous agents negotiating under incomplete information. Bargaining protocols in JADE. 188-page thesis. The coordination problems I formalized then are what LangGraph solves today.

  2. 2017

    ML Engineering — Pharma

    Sanofi. Demand forecasting for pharmaceutical distribution centers. 8% stock reduction. First lesson: ML in a regulated, politically sensitive environment requires as much change management as engineering.

  3. 2017–19

    Wave I — Big Data

    EDF. Real-time 360° Customer View on Spark/HBase. Enterprise-scale data engineering before it was standard at French utilities. The constraint: legacy Oracle systems that couldn't be replaced, only surrounded.

  4. 2019–21

    Wave II — Cloud Native & MLOps

    AI/ML platform on AWS & OpenShift: 100+ daily training jobs, feature store, CI/CD, model registry — built from scratch when MLOps was still a conference topic. Learned: governance without autonomy kills adoption.

  5. 2021–Now

    Wave III — GenAI & Agentic Architecture

    EDF Group (Senior). LangGraph agentic workflows, RAG, MCP, LLM governance across 10+ teams. The 2016 theoretical framework now deployed at enterprise scale — with all the production constraints theory never anticipated.

06 / Architecture Trade-offs

Opinions Grounded in Production.

A tool list proves nothing. What follows are architectural decisions where the answer wasn't obvious — and the reasoning that drove the choice.

LangGraph vs raw orchestration

Explicit state machines win in production.

LangChain's abstraction hides the state machine. In a 4-agent workflow with conditional branching and human-in-the-loop checkpoints, implicit state management becomes a debugging nightmare at scale. We moved to explicit LangGraph graphs — more verbose, every state transition observable, testable, and restartable. Trade: developer ergonomics for operational resilience. In production, you always choose resilience.

RAG vs fine-tuning

Wrong question. Right answer depends on the knowledge lifecycle.

RAG wins when the knowledge base changes frequently and you need audit trails. Fine-tuning wins when output format consistency matters and the domain vocabulary is stable. At EDF, the regulatory and contractual corpus updates quarterly — RAG was the only defensible architecture. Fine-tuning was answering the wrong question.

Feature stores: when they create more problems than they solve

Feature stores earn their place in ~40% of use cases.

Feature stores solve a real problem — training-serving skew — but introduce operational overhead that exceeds the value for most teams. At 100+ daily training jobs, we found the break-even point: feature stores are justified for sub-hour refresh cycles and cross-team feature reuse. For everything else, a versioned feature pipeline with documented contracts is simpler, more debuggable, and cheaper to operate.

MLflow vs custom model registry

Build custom only after you've hit the OSS ceiling.

MLflow's registry is sufficient for most production use cases. We customized exactly three things: upstream metadata schema enforcement, downstream deployment contracts, and rollback trigger logic. The instinct to build bespoke tooling is almost always wrong until you've exhausted the OSS tool at scale. We didn't exhaust MLflow for two years.

Coming

Architecture decision record: AutoCons-Radar RAG pipeline

Full ADR for the LLM-powered eligibility engine at EDF — model selection, chunking strategy, retrieval design, evaluation framework, failure modes. Publishing Q3 2025.

07 / Technical Reference

Tools used in production. Depth varies — ask me to draw the boundary between "comfortable in production" and "evaluated and rejected" for any of these.

Agentic AI & LLMs

Multi-Agent SystemsLangGraphLangChainLlamaIndexRAG PipelinesMCPMistral · Gemini · Ollamapgvector

MLOps & LLMOps

MLflowFeature StoreModel RegistryCI/CD GitLab / GH ActionsEvidentlyLightGBM · scikit-learnOptunaTime Series Forecasting

Cloud Native & Infrastructure

AWSOpenShiftKubernetesDockerTerraformKafkaSpark · AirflowS3 · DBT

API & Architecture Patterns

FastAPIMicroservicesEvent-Driven ArchitectureOpenAPIOracle · SAP Integration

Governance & Engineering Leadership

Architecture Review BoardFinOpsELK · Prometheus · GrafanaObservabilityCross-functional alignment

Foundations

PythonSQL · PySparkJava · JADE (MAS)Mathematics · StatisticsNeuro-Symbolic AI

08 / What I'm Building

Independent Consulting Practice

Senior Solution Architecture for enterprise AI platforms. Current: EDF DSIN Direction Commerce — GenAI, Agentic AI, MLOps at scale.

SeriesMind — early stage

Multi-Agent Time Series Platform

Six specialized autonomous agents, human-in-the-loop checkpoints, conformal prediction for distribution-free confidence intervals. The proof-of-work on the architecture decisions described above.

09 / Beyond the Screen

01

The Athlete

Former professional handball player. Today, cycling as commitment: each year I ride the Tour de France routes across Europe, stage by stage. Hyrox races fill the winters.

02

The Mind

Iyengar Yoga — precision and structural alignment as practice. Sustained interests in neuroscience, cognitive science, and contemplative traditions.

03

The Listener

Cosmic jazz: Ibrahim Maalouf, Dhafer Youssef, Avishai Cohen. Structured improvisation — the beauty of constraint.

04

The Aesthetic

Brutalism and neo-brutalist architecture. Structures that expose their raw logic and carry their weight honestly, without ornament.

Available for senior missions

Solution Architect AI · Agentic AI · MLOps · LLMOps · GenAI Platform

Paris region & remote · Minimum 6 months ·

Get in touch