We are looking for a Machine Learning Engineer to join an early-stage European startup developing AI-first platforms for research automation and enterprise innovation. The product leverages state-of-the-art LLMs, Retrieval-Augmented Generation (RAG), and multi-agent architectures to help users transform unstructured data into actionable insights. As a Senior ML Engineer, you’ll take ownership of RAG pipelines, data ingestion flows, and agentic LLM-based components. You will collaborate directly with the founders, shape technical architecture, and contribute to building cutting-edge AI systems used by researchers and innovation teams worldwide. Client – is a Switzerland-based startup focused on AI and LLM product innovation. Their platforms empower researchers and enterprises to manage large volumes of unstructured content (documents, feedback, competitive data) and interact with it via intelligent agents. The company is fully remote, grant-funded for the next 2 years, and committed to fast iteration and deep tech exploration. Requirements:

3+ years of experience in ML, data science, or analytics engineering roles Hands-on experience building at least two production-ready RAG systems Proven use of LangChain, LlamaIndex, or Langroid in real-world projects Strong knowledge of LLM embeddings (OpenAI, Cohere, HuggingFace) Experience with vector databases: Pinecone, Weaviate, Qdrant, PGVector Expertise in PDF parsing, OCR, and chunking techniques Integration experience with LLM APIs: GPT-4o, Claude, Gemini, or Bedrock Understanding of multi-agent orchestration, data pipelines, and context handling Upper-Intermediate spoken English or higher Nice to Have:

Familiarity with knowledge graphs and hybrid RAG optimization Previous experience working in a startup environment Background in information retrieval or NLP research Experience with latency/cost/accuracy optimization for LLM pipelines Responsibilities:

Design and maintain end-to-end RAG pipelines across two products Implement and optimize multi-source data ingestion from PDFs, feedback, and screenshots Integrate and orchestrate multi-agent LLM-based systems for tasks like retrieval, ranking, and QA Ensure performance, reliability, and cost-effectiveness of LLM usage Collaborate closely with co-founders and backend/frontend engineers Contribute to the evolution of AI product features and architecture Document system design and share best practices with junior contributors We offer:

Medical Insurance after 3 months probation period (can be used in Ukraine) Vacation (up to 20 working days) Paid sick leaves (10 working days) National Holidays as paid time off (11 days) Online English courses Accountant assistance and legal support Flexible working schedule, remote, office-based or hybrid format Fully-equipped perfect office space located in the city center (ready for work in blackouts) Direct cooperation with the customer Challenging projects in diverse business domains and a variety of tech stacks Online/offline teambuildings Volunteering culture development and support Your name Your email Subject Your message (optional)