AI LLM Architect - Manufacturing and Operations (All Genders)
Remote • Wuerzburg
Posted 2d ago
Job Location
Wuerzburg
Tech Stack
Remote Work Policy
Fully remote
Categories
AI Agent Engineer
About the job
As a hands-on AI/LLM Architect, you will be responsible for designing and building advanced AI systems for enterprises. This role involves a significant amount of architecture and engineering work across classical machine learning, generative AI, and agentic systems. You will translate requirements into architectural decisions, select design patterns, evaluate frameworks, and choose technologies that balance innovation with reliability. A key part of the role includes designing AI agent architectures, working with foundation models through fine-tuning and RAG, and engineering the AI context layer to ensure AI outputs are grounded and accurate. You will also design and validate systems against enterprise non-functional requirements like security, observability, and scalability, producing tangible engineering and architecture deliverables such as software components and detailed architecture artifacts.
Responsibilities
- Independently design, build, and deliver software components across the AI architecture, owning them end-to-end.
- Design and build AI agent architectures, including individual agents, their prompts, tools, skills, multi-agent orchestration, and memory systems.
- Design and implement agent orchestration patterns for task handoffs, communication, state management, and error recovery.
- Evaluate design options and technical approaches, making justified design choices balancing capability, cost, performance, and reliability.
- Design, build, and run evaluation strategies and harnesses to measure agent and system quality.
- Architect and implement foundation model integrations, selecting models and customization approaches.
- Design and build model adaptation and fine-tuning pipelines, applying knowledge of transformer-based architectures.
- Design and build the AI context layer, including context graph design, ingestion pipelines, and retrieval components.
- Build embedding, vector storage, and retrieval into end-to-end RAG pipelines.
- Design and implement context assembly and memory components for grounded, accurate outputs.
- Identify, design, and build reusable components and solution patterns.
- Design for cost efficiency and performance, optimizing model usage, inference patterns, and resource utilization.
- Design, build, and validate systems against enterprise non-functional requirements, implementing guardrails and defenses.
- Build governance controls including versioning, audit logging, and lineage tracking.
- Build observability into systems for monitoring, alerting, and cost tracking.
- Produce detailed architecture artifacts such as ADRs, blueprints, and diagrams.
- Continuously learn and apply new design patterns, frameworks, and technologies.
- Collaborate with cross-functional delivery teams to translate requirements into architecture decisions.
Requirements
- Hands-on experience in architecture and engineering of AI solutions.
- Experience with classical machine learning, generative AI, and agentic systems.
- Ability to translate requirements into concrete architecture decisions.
- Experience selecting design patterns, evaluating technical frameworks, and assembling reusable components.
- Experience designing AI agent architectures, including multi-agent orchestration, tool use, skills use, and memory systems.
- Hands-on experience with foundation models through fine-tuning, RAG, and custom model integration.
- Experience engineering the AI context layer, connecting knowledge bases, data sources, and content.
- Experience designing and validating systems against enterprise non-functional requirements (security, observability, governance, performance, scalability).
- Experience producing engineering and architecture deliverables like software components and architecture artifacts (ADRs, diagrams).
- Experience working with cross-functional delivery teams (data engineers, ML engineers, application developers).
- Deep expertise across the full AI architecture stack.
- Ability to develop expertise across the full AI architecture stack.
- Ability to sharpen engineering instincts on complex, real-world problems.
- Potential to grow into a lead or principal architect role.