AI research engineer

neuland.ai, Cologne, North Rhine-Westphalia, Germany

AI Research Engineer

Location: Onsite/Hybrid – Type: Full-time – Team: Applied AI Research

About the Role

We are seeking a highly motivated Research Scientist/Engineer to join our Applied AI Research team. In this role you will take ownership of advancing LLM‑driven Retrieval‑Augmented Generation (RAG) systems, small LLMs (sLLMs), and multimodal foundation models with a focus on scalability, efficiency, and real-world impact. You will design and implement novel architectures, fine‑tuning pipelines, and evaluation frameworks that push the boundaries of how enterprises and end‑users interact with large language and vision‑language models.

This is an opportunity to work at the intersection of cutting‑edge research and applied innovation—driving projects from conceptual research all the way to production‑ready solutions.

Responsibilities

• Research & Innovation : Investigate and prototype advanced methods for hybrid RAG pipelines (dense + sparse retrieval, agentic workflows, multimodal contexts).
• Model Optimization : Fine‑tune and optimize both large‑scale LLMs and lightweight sLLMs for efficient on‑device or edge deployment.
• Evaluation & Benchmarking : Build robust evaluation pipelines covering faithfulness, factual accuracy, latency, scalability, and cost trade‑offs.
• System Development : Implement scalable orchestration frameworks (e.g., LangChain, LlamaIndex, custom agents) to integrate LLMs with data, APIs, and tools.
• Deployment : Deliver production‑grade solutions on the Azure AI stack (or equivalent), ensuring performance, reliability, and compliance.
• Collaboration : Work cross‑functionally with product teams, engineers, and stakeholders to translate research into real‑world applications.
• Knowledge Sharing : Contribute to internal research reports, documentation, and open‑source projects when possible.

Requirements

• Strong programming skills in Python, with experience building ML pipelines end‑to‑end.
• Solid understanding of Transformers, LLM architectures, sLLMs, and multimodal models.
• Hands‑on experience with retrieval systems (vector databases, hybrid retrieval, embeddings).
• Familiarity with LLM APIs and frameworks (Azure OpenAI, Hugging Face, LangChain, etc.).
• Knowledge of model optimization techniques (LoRA, quantization, distillation, pruning).
• Demonstrated ability to take research from idea → prototype → deployment.

Preferred Qualifications

• Master’s or PhD in Computer Science, AI, NLP, Machine Learning, or related fields.
• Prior research or industry experience in RAG, LLM fine‑tuning, IR/NLP, or multimodal AI.
• Familiarity with evaluation benchmarks for LLM/RAG (RAGAS, MTEB, factuality/faithfulness metrics).
• Experience with cloud‑based AI workflows (Azure, AWS, GCP).
• Knowledge of distributed training/inference acceleration (DeepSpeed, Hugging Face Accelerate, Ray).
• Track record of publications, patents, or open‑source contributions in relevant areas.

What We Offer

• Opportunity to shape next‑generation multimodal RAG systems and small LLM deployments with real‑world impact.
• Exposure to cutting‑edge research and large‑scale deployments.
• Collaboration with a highly skilled team of researchers and engineers.
• Competitive compensation, benefits, and career growth opportunities.
• A culture that values applied innovation, safety, and trustworthiness in AI.

Seniority level

• Mid‑Senior level

Employment type

• Full‑time

Job function

• Engineering and Information Technology
• Technology, Information and Internet

#J-18808-Ljbffr