Offer summary

Qualifications:

Eligible to work in Germany or within the EU., C2 level proficiency in English., At least 3 successfully deployed AI projects, with expertise in NLP and generative AI., Strong Python skills and experience with AI pipelines..

Key responsabilities:

Develop and deploy scalable machine learning systems with a focus on privacy-preserving AI.

Build and optimize NLP applications using transformer models like BERT and GPT.

Create workflows for automated context-aware decision making and optimize models for resource efficiency.

Conduct benchmarking and evaluation of large language models and manage data processing pipelines.

Job description

The AI startup Xayn develops Noxtua, Europe’s first sovereign Legal AI. Noxtua helps lawyers analyze and draft legal documents and research legal questions while being legally competent and compliant. Hosted in the EU, Noxtua meets high standards of confidentiality in handling client data, professional secrecy (e.g. Section 203 German Criminal Code, Section 43e German Federal Code for Lawyers), and European data protection. Noxtua is powered by specialized proprietary AI models. The models are trained with high-quality legal data provided by the Legal AI Alliance which the tech startup Xayn initiated with the international business law firm CMS. This makes Noxtua the secure, independent, and specialized European Legal AI.

The Berlin-based AI company Xayn was born out of research at Oxford University and Imperial College London by Dr Leif-Nissen Lundbæk and Professor Michael Huth. Founded in 2017, Xayn’s academic vision remains, with a workforce comprised of approx. 30% PhDs. The startup has received investment funding of 19.5 million EURO from Global Brain Corporation, KDDI Open Innovation Fund, Earlybird, and Dominik Schiener.

Your Team

You will join our AI Team led by Felix (Head of AI), working closely with a group of approximately 5 AI experts. This highly collaborative team focuses on pushing the boundaries of generative AI, natural language processing, and privacy-preserving machine learning legal solutions.

Your Hiring Manager

Felix, our Head of AI, will guide you through your journey at Xayn. With deep expertise in AI systems, Felix leads with a passion for innovation and a collaborative approach, ensuring every team member thrives.

Your Responsibilities

Develop and deploy scalable machine learning systems, focusing on privacy-preserving AI
Build and optimize NLP applications using transformer models like BERT, GPT, and RAG
Create workflows using agentic frameworks for automated context-aware decision making
Optimize models for resource efficiency using techniques like quantization, pruning and distillation.
Using open-source ML frameworks (e.g., TensorFlow, PyTorch)
Develop AI pipelines, including retrieval-augmented generation systems
Conduct benchmarking and evaluation of large language models (LLMs)
Work with vector databases and manage data processing pipelines

Our Tech Stack

Programming Languages: Python

Frameworks: LangChain, LangGraph, LlamaIndex

Libraries: HuggingFace, Transformers, NumPy, Pandas, Pydantic, FastAPI, OpenAI & PyTorch

Deployment Tools: Docker

Cloud Infrastructure: AWS, GCP, Azure

MLOps: CI/CD pipelines for AI models, including monitoring and version control

Vector Databases: ElasticSearch, Qdrant, Pinecone

Ticket System: Atlassian JIRA

Repository: Github

CI/CD System: GitHub Actions

Documentation: Confluence

Communication: Slack

Office Application: MS365

Requirements

Residence & Work Permit: Eligible to work in Germany or within the EU.
Language: English proficiency at C2 level.
Experience: in AI development with at least 3 successfully deployed projects
NLP & Generative AI: Expertise in developing and deploying NLP and generative AI models
Open-Source Models: Solid experience with open-source models (e.g., LLAMA, Mistral, Cohere)
RAG: Knowledge in building RAG systems
Programming: Strong Python skills and experience with AI pipelines
Data: Familiarity with data processing, filtering, and augmentation

Optional:

Fine-tuning of pre-trained LLMs using custom datasets for domain adaptation
Proficiency in vector database management
Experience in deploying custom AI solutions with privacy considerations

Benefits

Working hours: Flexible working hours: Full-time (32- 40h/week).
Vacation: 26 days + December 24th & 31st off
Remote: 100% remote work possible (given a German residence), other countries upon request
Discounts: e.g. Urban Sports Club Membership
Equipment: Laptop (Lenovo or Mac), second screen, keyboard etc.

Sounds good? Then, we look forward to receiving your CV via our online application form.

Required profile