Bereits vergeben

Lass dir die nächste nicht entgehen — erhalte passende Stellen direkt per Mail.

Senior Full-Stack AI/LLM Engineer (all genders)

Remote
Vollzeit
vor 2 Monaten
Office In Leipzig, Berlin, Germany
Stellenbeschreibung

Key Responsibilities

LLM Application & Agentic Workflow Engineering

  • Prototyping & Design: Lead the prototyping and design of novel AI experiences, translating product requirements into scalable LLM architectures.
  • Advanced Agentic Systems: Architect, build, and deploy multi-agent and hierarchical agent workflows (using tools like LangGraph, AutoGen, or similar) to solve complex educational and medical problems.
  • RAG Implementation: Design, build, and optimize the Retrieval-Augmented Generation (RAG) pipeline for domain-specific knowledge retrieval, including selection of embedding models, vector databases (e.g., Pinecone, Weaviate), and indexing strategies.
  • Model Adaptation: Apply model adaptation techniques like Fine-Tuning, LoRA, and QLoRA to tailor pre-trained LLMs to our specific medical and educational datasets.
  • Evaluation & MLOps: Actively support the evaluation and testing of LLM applications, including defining metrics and integrating feedback loops to ensure performance, accuracy, and reduction of hallucinations.
  • API Development: Build and optimize high-performance, cost-effective APIs for LLM inference, ensuring scalability and robust integration.

Full-Stack Integration

  • Feature Implementation: Work across the full stack to integrate production-ready AI features into the existing platform, ensuring a seamless user experience.
  • Core Stack Development: Utilize React and TypeScript to build, maintain, and enhance the front-end and core backend services interacting with the AI layer.
  • Infrastructure & Deployment: Collaborate with DevOps to containerize, deploy, and monitor AI services on cloud infrastructure, ensuring reliability and adherence to medical data standards.

Your profile

  • Experience: 5 years of professional software development, including 1 year building and deploying production LLM applications.
  • LLM Expertise: Strong knowledge of prompt orchestration, advanced RAG systems, vector databases, model adaptation, and agentic (multi-agent, hierarchical) workflows.
  • Programming: Expert in Python for ML/LLM backends; strong full-stack ability with React and TypeScript.
  • Cloud & Deployment: Hands-on experience deploying and monitoring ML/LLM systems in cloud environments (AWS).
  • Education: Bachelor's or Master's in Computer Science, Engineering, or a related quantitative field.
  • Product Ownership: Proven ability to take AI projects from prototype to production, with a strong product mindset focused on user value and business outcomes.
  • Leadership & Communication: Excellent communication skills with the seniority to mentor others and drive technical decisions in a collaborative, cross-functional team.

Nice-to-Haves:

  • Experience in the EdTech or HealthTech sectors, particularly involving medical data.
  • Familiarity with data governance and privacy requirements (e.g., GDPR, HIPAA/PHI concerns).

What we offer

  • Flexible working hours and remote work are a given to enable you to achieve a good work-life balance.
  • You are part of a highly engaged, motivated, and professional Development team.
  • Your ideas are heard: We value employees who drive change with creativity. Because only with a diverse team and fresh ideas can we make an impact!
  • A comprehensive, structured HR and professional onboarding process with cross-departmental introductions and feedback sessions.
  • Take advantage of our complete Lecturio training platform for free for your personal and professional development.
  • Free access to coaching sessions and other mental health benefits.

This is a senior position focused on the applied layer of AI - prototyping, building, and deploying production-ready systems, not foundational model training.

Location: Remote (Time zones: UTC / UTC +1 / UTC -1 / UTC +2 / UTC -2)

Employment Type: Full-time

If this sounds interesting to you, please apply directly through our website via the 'Apply Now' button: https://jobs-lecturio.kenjo.io/senior-full-stack-ai-llm-engineer. If you have any questions about the role, please feel free to reach out at jobs@lecturio.de. Please include your resume and a cover letter outlining your relevant experience in your application.

We look forward to your application.