AI Engineer

Coface; Colombes; Hybrid; EUR 90,000 - 130,000; Full time

Job summary

Coface is seeking an experienced Senior Data & AI Engineer to lead the development of scalable data pipelines and operational AI solutions. You will work with Business Information teams to deliver innovative solutions using company, financial, and risk data, including LLM-powered applications and RAG frameworks.

Strong English communication is required. Key responsibilities include deploying AI solutions on cloud platforms (AWS/Azure/GCP), implementing guardrails for responsible AI, and

Qualifications

• Master's degree in Computer Science, Data Engineering, or related field.
• At least 5 years of experience in software or data engineering, with 2+ years in AI/Generative AI/LLMs.
• Strong Python and SQL with robust data pipeline design and maintenance.
• Experience building AI apps using OpenAI, Azure OpenAI, Claude, Gemini, or open-source LLMs.
• Experience with RAG architectures, vector databases, LangChain, LlamaIndex, Semantic Kernel.

Responsibilities

• Design, develop, and maintain scalable data pipelines (ETL/ELT) for AI, analytics, and BI.
• Build and deploy AI-powered solutions leveraging LLMs and Generative AI tech.
• Architect and implement Retrieval-Augmented Generation (RAG) using vector databases.
• Develop intelligent AI agents and multi-agent systems with prompt engineering.
• Integrate AI capabilities into enterprise apps via APIs and microservices on cloud platforms.
• Identify, evaluate, and mitigate AI-related risks; implement guardrails and responsible AI.
• Ensure GDPR compliance and governance across the AI solution lifecycle.
• Leverage expertise in corporate, financial, and risk data domains to address real-world challenges.
• Optimize AI workloads for performance, scalability, cost, latency, and token consumption.
• Collaborate with product managers, engineers, and stakeholders; document architecture and standards.

Skills

Python

SQL

LLMs

Generative AI

LangChain

LlamaIndex

Semantic Kernel

Data pipelines

AWS

Azure

GCP

Docker

Kubernetes

Vector databases

Education

Master's degree in Computer Science, Data Engineering or related field

Tools

OpenAI

Azure OpenAI

Claude

Gemini

LangChain

LlamaIndex

Semantic Kernel

Docker

Kubernetes

Job description

We are looking for an experienced Senior Data & AI Engineer to lead the development of scalable data pipelines and operational AI solutions. In this role, you will work closely with our Business Information teams to deliver innovative solutions based on company, financial, and risk data. Key responsibilities include implementing LLM-powered applications, generative AI use cases, RAG frameworks, and AI agents, while ensuring compliance with security and responsible AI standards. The emphasis is on deploying and integrating AI solutions into enterprise environments rather than training models from the ground up. Strong professional English communication skills are required.

Key Responsibilities

• Design, develop, and maintain scalable data pipelines (ETL/ELT), ensuring high data quality and reliability to support AI, analytics, and business intelligence initiatives.
• Build and deploy AI-powered solutions leveraging Large Language Models (LLMs) and Generative AI technologies (GPT, Claude, Gemini, and open-source models)
• Architect and implement Retrieval-Augmented Generation (RAG) solutions using vector databases to deliver accurate, context-aware AI applications.
• Develop intelligent AI agents and multi-agent systems, apply advanced prompt engineering, orchestration frameworks, and tooling such as LangChain, LlamaIndex, and Semantic Kernel.
• Integrate AI capabilities into enterprise applications through APIs and microservices and manage deployment and operations on cloud platforms such as AWS, Azure, or GCP.
• Identify, evaluate, and mitigate AI-related risks, including prompt injection, data leakage, and hallucinations, while implementing robust guardrails and Responsible AI best practices.
• Ensure compliance with data privacy regulations (GDPR) and emerging AI governance frameworks throughout the entire AI solution lifecycle.
• Leverage expertise in business information domains, including corporate, financial, and risk data, to design solutions that address real-world business challenges.
• Optimize AI workloads for performance, scalability, cost efficiency, latency, and token consumption in production environments.
• Collaborate closely with product managers, software engineers, data professionals, and business stakeholders to translate requirements into technical solutions, while documenting architecture, standards, and best practices.

You are likely to be successful in this role if you have:A Master's degree in Computer Science, Data Engineering, or a related field.At least 5 years of experience in software or data engineering, including 2+ years working with AI, Generative AI, or Large Language Models (LLMs).Strong expertise in Python and SQL, with hands-on experience designing and maintaining robust data pipelines.Proven experience building AI applications using technologies such as OpenAI, Azure OpenAI, Claude, Gemini, or open-source LLMs.Experience implementing RAG architectures, vector databases, and AI orchestration frameworks such as LangChain, LlamaIndex, or Semantic Kernel.Knowledge of cloud environments such as AWS, Azure, or GCP, including deploying AI solutions in production.A solid understanding of AI security, responsible AI practices, data privacy, and governance requirements.Excellent communication skills and the ability to collaborate effectively with both technical and business stakeholders.Fluent professional English, both written and spoken.Personal qualities we value:Curiosity and a passion for innovation.Pragmatic problem-solving skills.A collaborative mindset and strong ownership.The ability to thrive in a fast-evolving AI environment while maintaining high quality and security standards.What will set you apart:Experience with AI agents and multi-agent systems.Familiarity with AI guardrails, model evaluation, and AI governance frameworks.Knowledge of financial, corporate, or risk information domains.Experience with Docker, Kubernetes, and modern software engineering practices.