Freelance AI Engineer | RAG, Agents & Enterprise AI in Olching

Arantic Digital is a software and AI company building modern digital products and enterprise solutions.

We focus on practical applications of AI, automation, and intelligent software that solve real business problems.

We are a small, technology driven team that values ownership, fast execution, strong engineering decisions, and building products that people actually enjoy using.

We are looking for an experienced AI Engineer to work with the Arantic team, with a strong focus on Retrieval Augmented Generation (RAG) and enterprise AI systems.

Location Remote, worldwide.

We welcome applications globally.

We are building a self hosted enterprise AI platform that connects company knowledge, AI assistants, and agents with business tools and systems.

Our goal is to help organizations find reliable answers and carry out useful actions while maintaining control over their data, permissions, and approvals.

RAG is a central part of the platform, alongside agent workflows, tool integrations, and a clear, intuitive user experience.

AI is deeply embedded in how we build software.

AI tools are part of our everyday development workflow.

We expect you to use them effectively, guide their output, critically review what they produce, and take ownership of the final result.

Strong engineering judgment, architectural thinking, and a good understanding of the product and user experience matter more to us than simply writing code.

What you will work on Build and improve RAG pipelines covering document ingestion, chunking, indexing, retrieval, and answer generation.

Improve retrieval quality using embeddings, hybrid search, reranking, and metadata filtering.

Build evaluation systems to measure retrieval quality, answer accuracy, grounding, and overall system performance.

Develop AI assistant and agent workflows that combine enterprise knowledge with tools and APIs, including MCP integrations.

Build systems that respect user permissions and provide traceable answers, controlled actions, and human approvals.

Integrate LLMs and optimize systems for reliability, latency, quality, and cost.

Help shape technical architecture, review AI generated code, and turn product requirements into reliable solutions ready for production.

What you bring At least 3 years of professional software engineering experience, ideally with experience in backend, platform, or AI systems.

Practical experience building, shipping, and operating RAG or LLM based systems in production, beyond demos and prototypes.

A strong understanding of vector databases, embedding models, retrieval strategies, and modern RAG architectures.

Strong software engineering skills, with the ability to work effectively in Type Script and Python.

Experience integrating LLMs into applications, ideally including tool calling or agent workflows.

Experience designing systems beyond individual features, including architecture, APIs, data flows, observability, reliability, and performance.

Confidence using AI coding tools while critically reviewing, testing, and validating their output.

The ability to think beyond individual tasks and understand architecture, product requirements, and the broader system.

An independent and pragmatic working style, clear communication, and genuine interest in the product you are building.

Our team works in English, so strong written and spoken English is required.

A degree in Computer Science, Software Engineering, AI, or a related field is a plus, but we care more about what you have built and the engineering decisions you have made.

Experience with self hosted models, Postgre SQL with pgvector, evaluation frameworks, MCP, or retrieval systems that respect user permissions is a plus.