AI/ML Engineer

Join our team!

Key Responsibilities

• Design and implement a knowledge management system for document classification and labeling, leveraging RAG pipelines.
• Utilize embedding models to extract, retrieve, and classify information efficiently.
• Design, train, fine-tune, and deploy embedding models using frameworks such as PyTorch, TensorFlow, and Hugging Face Transformers.
• Optimize embedding-based retrieval strategies for high performance and accuracy.
• Develop and integrate RAG pipelines for document processing, chunking, and embedding-based retrieval.
• Collaborate with cross-functional teams to ensure smooth integration of ML models with downstream generative and question-answering tasks.
• Implement document chunking techniques and optimize embedding-based retrieval for scalable and efficient knowledge extraction.
• Leverage vector databases (e.g., FAISS, Pinecone, Milvus) to store and query embeddings.
• Build and deploy APIs and microservices to expose ML models and facilitate seamless interaction between components.
• Ensure the system is modular, secure, and scalable for real-world applications.
• Work closely with product managers, data engineers, and other stakeholders to translate business requirements into technical solutions.
• Document methodologies, processes, and results for internal and external stakeholders.

Required Skills and Qualifications

• Proven expertise in designing, implementing, training, and fine-tuning embedding models.
• Strong understanding of text embedding generation and applications in search and classification tasks.
• Ability to design and implement end-to-end Retrieval-Augmented Generation pipelines.
• Knowledge of document chunking techniques and optimal embedding-based retrieval strategies.
• Strong coding skills in Python.
• Hands-on experience with PyTorch, TensorFlow, and Hugging Face Transformers.
• Proficiency in working with vector databases (e.g., FAISS, Pinecone, Milvus) for storage and retrieval of embeddings.
• Experience building APIs and microservices to expose machine learning models for seamless integration with other systems.

Preferred Skills

• Familiarity with natural language processing (NLP) techniques, such as semantic search and named entity recognition.
• Knowledge of containerization technologies (Docker).
• Experience in building and deploying scalable machine learning solutions in production environments.
• Strong problem-solving skills and ability to work in an agile environment.

What we offer

• Being part of a business area that is growing with limitless opportunities.
• Dynamic environment in a technologically advanced organization.
• Opportunities for further professional training and certification.
• Opportunity to work with a great team of people, on various interesting projects.
• Many benefits that support your personal life: flexible working hours, family-friendly business, hybrid work model, sports and cultural activities...