Personal details

Jijun T. - Remote full-stack developer

Jijun T.

Senior AI Engineer | AI Agents & Data Platforms
Based in: 🇫🇷 France
Timezone: Paris (UTC+1)

About

Senior AI Engineer and Backend Developer specializing in AI agents, Generative AI, data platforms, and distributed systems. Experienced in building production AI applications and large-scale data systems using Python, TypeScript, Node.js, PostgreSQL, Kafka, Kubernetes, and cloud platforms.

Hands-on experience with agentic AI, RAG, LLM applications, machine learning, OCR, and cloud-based data pipelines across AWS, Azure, and GCP. Strong background in designing scalable backend services, AI workflows, ETL/streaming platforms, and full-stack interfaces, with a focus on reliable production systems and real-world business impact.

Work Experience

AI Engineer / Big Data Engineer
Jems Group | Apr 2026 - Present
Python
Node.js
PostgreSQL
TypeScript
Google BigQuery
React
Google Cloud Platform
Multi agent systems
Airflow
Google Cloud Run
Supabase
Prompt Engineering
Generative AI
LLM
AI Ethics
Vertexai
RAG
Ai agent
  • Design and develop AI agents capable of automating complex gameplay and business workflows using Python and reinforcement learning techniques.
  • Develop and evaluate agentic AI systems and AI-assisted development workflows, including technologies such as Claude Code and other modern agent frameworks.
  • Design and implement RAG-based AI applications using Vertex AI and enterprise data sources.
  • Build human-machine interaction systems using React, TypeScript, and Python.
  • Design and maintain database schemas and production data workflows using PostgreSQL and Supabase.
  • Maintain large-scale video streaming data platforms supporting TV5Monde workloads.
  • Develop and maintain cloud-based data pipelines using BigQuery, Cloud Run, and Airflow.
  • Work across AI, data engineering, backend, and frontend components to deliver production-ready systems.
  • Create technical documentation and operational procedures for AI systems and production environments.
Big Data Engineer / Full-Stack Developer
Ellisphere | Aug 2025 - Feb 2026
Java
Scala
Node.js
Angular
PostgreSQL
Unit Testing
Jenkins
JAXB
Cassandra
Elasticsearch
Streaming
XML Schema
TypeScript
Docker
ETL
NLP
Code Review
Apache Kafka
SVN Repository
Grafana
Agile
Prometheus
CI/CD
REXX
Qwik framework
  • Designed and developed new features for batch and streaming data pipelines using Scala and Java.
  • Built and maintained distributed data infrastructure using Kafka, Cassandra, Elasticsearch, and Qlik.
  • Developed full-stack applications using Angular, TypeScript, and Node.js.
  • Designed and maintained database schemas and data models using PostgreSQL and Oracle.
  • Implemented production monitoring and observability using Prometheus and Grafana.
  • Built and maintained CI/CD workflows using Docker and Jenkins.
  • Collaborated with data analysts to translate business requirements into scalable technical solutions.
  • Contributed to data governance, technical documentation, and enterprise data mapping.

Projects

NLP Features Development
2025
Java
Scala
Angular
XML
Jenkins
Apache Kafka
SVN Repository
Grafana
Prometheus
Spark ml Lib
Integrated into a team of 9 people working in Agile (developers, product managers). These pipelines process judicial and financial data of European companies, the business challenge being to guarantee 100% reliability of data. - Design and development of Natural Language Processing (NLP) features in Java and Scala - Implementation of a pipeline validating daily XML files via JAXB using XSD schemas - Deployment and maintenance of 4 batch ETL chains in REXX - Creation of an Angular 20 UI for business data visualization - Administration of Kafka topics and streams for data streaming - Implementation of observability (SLO/monitoring) via Prometheus and Grafana dashboards - Management of CI/CD pipelines (GLPI, Jenkins, SVN) including documentation, unit tests and code reviews
RAG for Internal LLM
2024
Python
Java
Scala
Bash
Jenkins
Elasticsearch
Jira
GitLab
Google Cloud Platform
Confluence
Apache Kafka
Airflow
Dataflow
Orange, French telecommunications leader, undertook the migration of its data to GCP Cloud. Within a team of 15 people, I accompanied this transition by optimizing ETL pipelines. The business challenge was to ensure continuity of Big Data applications while controlling Google Cloud costs. - Design and development of new features for ETL chains based on Kafka, Spark and ElasticSearch - Development and implementation of a RAG (Retrieval-Augmented Generation) solution for an internal LLM (Dinootoo) - Operational maintenance of Big Data applications (Kafka, Spark, NiFi, ElasticSearch, Airflow) - Testing applications from on-premise to GCP environments (Cloud Composer, BigQuery, Big Table) - Update and optimization of GCP DataFlow packages in Python - Industrialization via CI/CD integration (GitLab CI, Jenkins, GCP) - Participation in Agile (Scrum) rituals via JIRA/Confluence

Education

Sorbonne University
Master's degree・Mathematical Engineering
Sep 2019 - Dec 2021
Sorbonne University
Bachelor's degree・Mathematics
Sep 2016 - Jul 2019

Certifications & Awards

Claude Certified Architect – Foundations
Anthropic | Aug 2026
Arc Certified Remote Developer
Arc.dev | Feb 2025