AI Platform Engineer (m/f/d)

Jedox

1d•Hybrid

About The Position

As an AI Platform Engineer, you will design and deliver reliable, secure and high-performing AI systems that transform the way organisations interact with data and automate workflows. You will be responsible for ensuring that all AI solutions meet production standards, deliver quantifiable value, and align with Jedox's focus on impactful results and continuous enhancement.

Requirements

8+ years in software engineering, including 3+ years delivering production-grade AI applications
Proven experience building and scaling enterprise AI solutions used by real users
Strong expertise in LLMs, RAG, and AI agents, including multi-agent systems and business process integration
Solid programming skills (Python) and experience with modern development practices (APIs, Docker, CI/CD)
Strong understanding of cloud-native architectures (especially Azure), vector databases, and semantic search
Hands-on experience with leading AI platforms (e.g., Azure OpenAI, AWS Bedrock, Copilot Studio)
Familiarity with AI frameworks (e.g., LangChain, LangGraph), observability, and AI governance
Excellent English communication skills are required

Responsibilities

Design and operate AI platforms: Build and manage the enterprise AI platform, integrating multiple LLM providers with routing, fallback strategies and cost control.
Develop reusable AI services: Develop scalable APIs and services to support agents, copilots and business applications throughout the organisation.
Build intelligent agents and workflows: Design autonomous and multi-agent systems capable of reasoning, planning and executing complex business processes.
Enable enterprise integrations: Drive end-to-end automation by connecting AI solutions to enterprise platforms such as Microsoft 365, SharePoint, Salesforce and Jedox.
Implement RAG architectures: Develop advanced retrieval systems using hybrid search, vector databases and semantic indexing to ensure accurate, grounded outputs.
Optimize AI performance: Ensure high system reliability while monitoring and improving latency, cost efficiency and inference performance.
Establish evaluation frameworks: Define metrics and testing strategies to ensure the accuracy of the AI, detect hallucinations, and evaluate its overall quality.
Ensure AI safety and governance: Maintain compliance and trustworthiness by implementing guardrails, monitoring systems and governance frameworks.
Manage AI lifecycle: Oversee prompt versioning, model management and CI/CD pipelines to maintain robust production deployments.