Applied AI Engineer

Delphi; Deutschland; Remote; EUR 65.000 - 85.000; Vollzeit

Zusammenfassung

A leading technology company in Germany is seeking an experienced Applied AI Engineer with a focus on LLMs. The role involves architecting backend systems, optimizing AI performance through prompt engineering, and creating AI features that enhance user experience. Ideal candidates will have 4-5 years of experience in software engineering and 1-2 years specifically in AI. Join a dynamic team to drive impactful projects and advance state-of-the-art technologies.

Qualifikationen

• 4-5 years of experience in software engineering, including 1-2 years in AI.
• Deep understanding of LLMs and experience with optimization techniques.
• Comfortable with scalable backend systems and AI-powered feature development.

Aufgaben

• Architect and implement improvements to AI mind architecture.
• Optimize LLM performance using advanced prompt engineering.
• Drive retrieval-augmented generation and context engineering.

Kenntnisse

Understanding of LLMs

Prompt engineering

Python

Backend system architecture

Graph-based retrieval systems

AWS/cloud infrastructure

Jobbeschreibung

Overview

We are seeking a highly skilled Applied AI Engineer with at least 4-5 years of experience, including 1-2 years specifically in AI. You should possess a deep understanding of LLMs, proven ability to optimize their performance through advanced prompt engineering, and mastery of Python for high-scale applications.

You will be comfortable architecting scalable backend systems while building AI-powered features that directly impact user experience and product outcomes. Bonus points if you have previous experience with graph-based retrieval systems, AWS / cloud infrastructure, and hands-on model fine-tuning.

What you'll do

• Architect and implement improvements to the backbone of Delphi's AI mind architecture, powered by knowledge graphs.
• Apply deep expertise in LLMs to push their performance and optimize through advanced prompt engineering techniques.
• Take ownership of retrieval-augmented generation (RAG) and context engineering, utilizing evaluation frameworks for LLM performance optimization.
• Bridge traditional software engineering with ML/AI systems, translating research into practical, scalable solutions.
• Define success metrics and evaluate the quality of digital mind outputs.
• Build AI-powered features that directly impact user experience and product outcomes.