Update 2026-06-27 & Add "Selected Projects"

2026-07-04 20:02:45 +02:00 · 2026-07-04 20:02:45 +02:00 · 1e28706bab
parent aa4c934300
commit 1e28706bab
7 changed files with 140 additions and 70 deletions
--- a/cv/cv.typ
+++ b/cv/cv.typ
@ -176,12 +176,10 @@
          // line 2: degree and date
          #text(weight: "semibold", size: 9.0pt, fill: luma(30.6%))[#edu.what #h(1fr)
            #start #sym.dash.en #end] \
-
          #if edu.why != none and edu.why.len() > 0 {
-            edu.why
-            // for hi in edu.why [
-            //   - #text(weight: "light")[#eval(hi, mode: "markup")]
-            // ]
+            for hi in edu.why [
+              - #text(weight: "light")[#eval(hi, mode: "markup")]
+            ]
          }
        ]
      }
@ -189,6 +187,42 @@
  }
 }

+#let cvprojects(lang, info, isbreakable: true) = {
+  let projects = info.projects
+  if projects != none {
+    block[
+      == #projects.title
+      #for project in projects.content {
+        // parse ISO date strings into datetime objects
+        let start = utils.strpdate(lang, project.startDate)
+        let end = utils.strpdate(lang, project.endDate)
+        // create a block layout for each project entry
+        block(
+          width: 100%,
+          breakable: isbreakable,
+        )[
+          // line 1: project name
+          #if project.url != none [
+            *#link(project.url)[#project.what]* \
+          ] else [
+            *#project.what* \
+          ]
+          // line 2: organization and date
+          #if "with" in project and project.with != none [
+            #text(style: "italic")[#project.with] #h(1fr) #start #sym.dash.en #end \
+          ]
+          // summary or description
+          #if "why" in project and project.why != none [
+            #for hi in project.why [
+              - #text(weight: "light")[#eval(hi, mode: "markup")]
+            ]
+          ]
+        ]
+      }
+    ]
+  }
+}
+
 #let cvaffiliations(lang, info, isbreakable: true) = {
  if info.affiliations != none {
    block[
@ -221,37 +255,6 @@
  }
 }

-#let cvprojects(lang, info, isbreakable: true) = {
-  if info.projects != none {
-    block[
-      == Projects
-      #for project in info.projects {
-        // parse ISO date strings into datetime objects
-        let start = utils.strpdate(lang, project.startDate)
-        let end = utils.strpdate(lang, project.endDate)
-        // create a block layout for each project entry
-        block(
-          width: 100%,
-          breakable: isbreakable,
-        )[
-          // line 1: project name
-          #if project.url != none [
-            *#link(project.url)[#project.name]* \
-          ] else [
-            *#project.name* \
-          ]
-          // line 2: organization and date
-          #text(style: "italic")[#project.affiliation] #h(1fr) #start #sym.dash.en #end \
-          // summary or description
-          #for hi in project.highlights [
-            - #eval(hi, mode: "markup")
-          ]
-        ]
-      }
-    ]
-  }
-}
-
 #let cvawards(lang, info, isbreakable: true) = {
  if info.awards != none {
    block[
--- a/data/education.yaml
+++ b/data/education.yaml
@ -6,7 +6,7 @@ content:
    endDate: 2021-09-01
    url: https://math-info.u-paris.fr/
    what: 
-      en: Double Master's Degree in Computer Science and Mathematics (Data Science)
+      en: Double Master's Degree in Computer Science and Mathematics (Data Science), Highest Honours
      fr: Double Master Mathématiques & Informatique (Sciences des données)
    with: Université de Paris
    where: 
@ -14,5 +14,5 @@ content:
      fr: Paris (75)
    why:
      en:
-        - Highest Honours
+        # - Highest Honours
      fr:
--- a/data/experience.yaml
+++ b/data/experience.yaml
@ -1,5 +1,5 @@
 title:
-  en: Work Experience
+  en: Professional Experience
  fr: Expérience Professionnelle
 content:
  - where:
@ -34,15 +34,15 @@ content:
            - "Mise en œuvre des bonnes pratiques de développement logiciel : tests, revues de code, supervision et support en production."
          en:
            - Designed and implemented an event-driven monitoring platform for 200+ applications running on the data lake.
-            - Led the migration of a business-critical Spark application from Spark 2 to Spark 3 while ensuring compatibility and while maintaining production continuity.
+            - Led the migration of a business-critical Spark application from Spark 2 to Spark 3, ensuring compatibility and production continuity.
            - Optimized ETL pipelines for finance data; reduced resources usage by more than 50%.
            - Developed internal reporting services and APIs used by business teams.
            - Applied software engineering best practices including testing, code reviews, monitoring and production support.
      - startDate: 2022-02-04
        endDate: 2025-02-14
        what: 
-          en: Data Engineer (Consultant) - Natixis
-          fr: Data Engineer (Consultant) - Natixis
+          en: Data Engineer (Consultant) - Natixis CIB
+          fr: Data Engineer (Consultant) - Natixis CIB
        technologies:
          - Scala
          - Kafka
@ -53,12 +53,12 @@ content:
          - Git
        why:
          en:
-            - Designed, implemented and monitored a complex Kafka producer computing and sending up to 1 billion messages per day.
-            - Implemented distributed Spark applications for large-scale financial data processing.
+            - Designed and implemented a high-throughput Kafka producer publishing up to 1 billion messages per day to accelerate PnL data distribution.
+            - Implemented distributed Spark applications for large-scale risk data processing like the prudent valuation adjustments.
            - Optimized and maintained production ETL pipelines for regulatory data; reduced resources usage by 80%.
          fr:
-            - Conception, développement et supervision d'un producteur Kafka traitant jusqu'à un milliard de messages par jour.
-            - Développement d'applications Spark distribuées pour le traitement de données financières à grande échelle.
+            - Conception, développement et supervision d'un producteur Kafka traitant jusqu'à un milliard de messages par jour pour le transfert de PnL inter-application.
+            - Développement d'applications Spark distribuées pour le traitement de données financières à grande échelle comme les calculs de réserves.
            - Optimisation et maintenance de pipelines ETL en production pour des données réglementaires, réduisant la consommation de ressources de 80 %.
  - where:
      en: Montrouge, France
@ -81,9 +81,9 @@ content:
          - XGBoost
          - Git
        why:
-          - en: "Engineered features via network modeling \\& analysis giving a 10\\% score improvement for prediction models"
+          - en: "Engineered graph-based features that improved prediction model performance by 10%."
            fr: Conception de variables (Feature Engineering) par modélisation et analyse de graphes, améliorant de 10 % les performances des modèles de prédiction.
-          - en: Developed a multi-environment pipeline execution program enabling the use of tools missing in one or another
+          - en: Developed a multi-environment pipeline execution framework enabling consistent workflows despite platform-specific tool availability.
            fr: Développement d'un programme d'exécution de pipelines multi-environnements permettant l'utilisation d'outils indisponibles selon les plateformes.
  - with:
      en: University Association IP7
--- a/data/projects.yaml
+++ b/data/projects.yaml
@ -0,0 +1,60 @@
+title:
+  en: Selected Projects
+  fr: Projets Personnels
+content:
+  - startDate: 2020-10-17
+    endDate:
+      en: present
+      fr: actuellement
+    url:
+    what: 
+      en: Personal Portfolio & Ledger Platform
+      fr: Automatisation de mon Livre de Compte Personnel
+    why:
+      en: 
+        - Built a Python, later Clojure, data ingestion pipeline to fetch, cache, and persist historical market data (ETFs, equities, and FX) for a personal Beancount ledger.
+        - Built an ETL pipeline to ingest, normalize, and reconcile CSV bank statements into the same Beancount ledger.
+        - Maintained historical price and FX time series to accurately value investment holdings and foreign-currency transactions.
+      fr: 
+        - Développement d'un pipeline d'acquisition de données en Python, puis en Clojure, pour la collecte, la mise en cache et le stockage de données historiques de marché (actions et devises).
+        - Conception et développement d'un pipeline ETL permettant l'ingestion, la normalisation et le rapprochement de relevés bancaires CSV dans un registre comptable Beancount unifié.
+        - Maintenance d'un historique de taux de change permettant la conversion précise de dépenses en devises vers une devise de référence.
+  - startDate: 2020-09-10
+    endDate:
+      en: present
+      fr: actuellement
+    url:
+    what:
+      en: Personal Infrastructure
+      fr: Infrastructure Personnelle
+    why:
+      en:
+        - Designed and operate a self-hosted infrastructure built on Proxmox VE, hosting containerized and virtualized services for development, automation, storage, and home automation.
+        - Deployed and maintain workflow orchestration (Airflow), CI/CD (Jenkins), Git hosting (Forgejo), centralized PostgreSQL, reverse proxying (Caddy), and automated backup solutions.
+        - Manage a dedicated OPNsense firewall/router providing network security, routing, and secure remote access through WireGuard.
+        - Host additional services on a Hetzner VPS, including a self-hosted task management platform and a personal website.
+        - Operate Home Assistant with a Zigbee mesh network, Frigate-based IP camera detection, and Immich with automated off-site backups.
+      fr:
+        - Conception et administration d'une infrastructure auto-hébergée sous Proxmox VE pour le développement, l'automatisation, le stockage et la domotique.
+        - Déploiement et maintenance Airflow, Jenkins, Forgejo, PostgreSQL, Caddy et des solutions de sauvegarde automatisées.
+        - Administration d'un pare-feu OPNsense assurant la sécurité du réseau et l'accès distant sécurisé via WireGuard.
+        - Hébergement de services sur un VPS Hetzner, dont une plateforme de gestion de tâches et un site web personnel.
+        - Exploitation de Home Assistant, un réseau Zigbee, Frigate et Immich avec sauvegardes externalisées automatisées.
+  - startDate: 2025-01-01
+    endDate: 2025-08-01
+    url:
+    what:
+      en: Statistical Analysis for Medical Research
+      fr: Analyse Statistique pour de la Recherche Médicale
+    why:
+      en: 
+        - Performed statistical analysis in R for a medical doctoral thesis investigating the relationship between vitamin C levels and frailty in elderly patients.
+        - Produced statistical outputs and visualizations to support the interpretation of the study's findings.
+      fr:
+        - Conduite des analyses statistiques sous R pour une thèse de doctorat en médecine étudiant l'association entre les taux de vitamine C et la fragilité des patients âgés.
+        - Élaboration des analyses, tests statistiques et visualisations ayant contribué à l'interprétation des résultats de l'étude.
+
+
+        
+
+
--- a/data/skills.yaml
+++ b/data/skills.yaml
@ -9,15 +9,15 @@ content:
      - Python
      - Scala
      - SQL
+      - Clojure
      - Java
      - R
-      - Clojure
      - C
      - C++
      - Bash
  - title:
-      fr: Data Engineering
-      en: Data Engineering
+      fr: Data Engineering & Systèmes Distribués
+      en: Data Engineering & Distributed Systems
    content:
      - Spark / PySpark
      - Kafka
@ -25,21 +25,36 @@ content:
      - Hadoop
      - DuckDB
      - BMC Control-M
+  - title:
+      fr: Bases de données
+      en: Databases
+    content:
+      - PostgreSQL
+      - MySQL
+      - SQLite
+      - Apache Hive
+      - Neo4j
+      - Cassandra
+      - Trino
  - title:
      fr: Cloud & Infrastructure
      en: Cloud & Infrastructure
    content:
      en:
        - Docker
+        - AWS (EC2, S3, IAM)
+        - GCP (BigQuery)
+        - Proxmox VE
+        - Linux
+        - Terraform
        - Kubernetes
-        - AWS (Working knowledge)
-        - GCP (Working knowledge)
-        - Proxmox VE
      fr:
-        - AWS (Bonnes connaissances)
-        - GCP (Bonnes connaissances)
-        - Proxmox VE
        - Docker
+        - AWS (EC2, S3, IAM)
+        - GCP (BigQuery)
+        - Proxmox VE
+        - Linux
+        - Terraform
        - Kubernetes
  - title: CI/CD
    content:
@ -54,20 +69,9 @@ content:
      - Polars
      - Numpy
      - Spacy
-  - title:
-      fr: Bases de données
-      en: Database systems
-    content:
-      - PostgreSQL
-      - MySQL
-      - SQLite
-      - Apache Hive
-      - Neo4j
-      - Cassandra
-      - Trino
  - title:
      fr: Frameworks Web
-      en: Web Frameworks
+      en: Frameworks
    content:
      - Spring
      - Flask
--- a/data/summary.yaml
+++ b/data/summary.yaml
@ -1,2 +1,3 @@
-en: Software Engineer / Data Engineer with 4+ years of experience building distributed data platforms and large-scale data processing systems. Experienced in designing event-driven architectures, developing production Spark and Kafka applications, and improving the performance, scalability, and reliability of critical data pipelines.
+en: Software Engineer / Data Engineer with 4+ years of experience designing and building distributed data platforms and large-scale data processing systems. Experienced in designing event-driven architectures, developing production Spark and Kafka applications, and improving the performance, scalability, and reliability of critical data pipelines.
+# en: Software Engineer / Data Engineer with 4+ years of experience building distributed data systems for investment banking. Experienced designing high-throughput Kafka and Spark applications, developing scalable data platforms, and applying software engineering best practices to production data systems.
 fr: Software Engineer / Data Engineer avec plus de 4 ans d'expérience dans la conception et l'exploitation de plateformes de données distribuées et de systèmes de traitement de données à grande échelle. Expérience dans la conception d'architectures orientées événements, le développement d'applications Spark et Kafka en production ainsi que l'amélioration des performances, de la scalabilité et de la fiabilité de pipelines de données critiques.
--- a/main.typ
+++ b/main.typ
@ -9,6 +9,7 @@
    education: yaml("data/education.yaml"),
    skills: yaml("data/skills.yaml"),
    languages: yaml("data/languages.yaml"),
+    projects: yaml("data/projects.yaml"),
  ))

  let uservars = (
@ -48,6 +49,7 @@
  cvwork(language, cvdata)
  cveducation(language, cvdata)
  cvlanguages(language, cvdata)
+  cvprojects(language, cvdata)
  cvskills(language, cvdata, sortLexically: false)
  endnote()
 }