Machine Learning Engineer | Python | Pytorch | Natural Language Processing | LLM | Large Language Models | Remote, Europe
About Us
We build AI assistants that make technical knowledge instantly accessible. As a research engineer, you will work on advancing our system’s ability to answer increasingly complex technical questions. Our technology is already deployed on real-world developer documentation, where users can query information directly through an integrated AI assistant.
The Challenges You’ll Work On
* Evaluating a retrieval-augmented-generation (RAG) system in production without labelled data
* Designing your own benchmarks from scratch
* Building an agentic retrieval pipeline that adapts between fast and more thorough query strategies
* Fine-tuning embeddings or reranking models
What You’ll Do
* Collaborate closely with the core team and software engineers
* Stay up-to-date with the latest research and apply new ideas to real product challenges
* Design, run and analyse experiments to push system performance
You Might Be a Great Fit If You Have
* A Master's or PhD in Computer Science, Machine Learning, Mathematics, Statistics, or a related field
* Strong knowledge of machine learning, deep learning (including LLMs), and natural language processing
* Hands‑on experience training, fine‑tuning, and deploying LLMs
* Experience working with vector databases, search indices, or data stores for retrieval use cases
* Significant experience building evaluation systems for search or language models
* Familiarity with information retrieval techniques (e.g., lexical search, dense vector search)
* Comfort working in a fast‑moving environment with ambiguous problem spaces
* A desire to learn more about ML research
Please note that this position is fully remote in Europe but you MUST have the right to work in your country of residence.
#J-18808-Ljbffr