ML Engineer (LLM)

We are an Innovation hub based, which creates vibrant startup ecosystems and technologies for AdTech & MarTech projects.

We are looking for an ML Engineer (LLM) for our Product Team!

Responsibilities

• Optimize model inference for performance and cost, using techniques like quantization and LoRA.
• Manage the end-to-end deployment lifecycle of models into a production environment.
• Take projects from a prototype (e.g., a Jupyter notebook) to a fully integrated, production-grade service.
• Collaborate with software developers and product managers to define requirements and implement solutions.

Requirements

• Proven experience in Python and its core ML ecosystems.
• Hands-on experience in deploying, fine-tuning, and inferencing LLMs or other deep learning models in a production setting.
• Experience with cloud platforms (AWS, GCP, or Azure) and containerization technologies (Docker, Kubernetes).
• Ability to work independently and manage the full lifecycle of a machine learning service.

Nice to have

• Experience with OpenAI's API and other commercial LLM services.
• Familiarity with MLOps tools for orchestration and monitoring (e.g., MLflow, Kubeflow, etc.).
• Understanding of NLP tasks relevant to our products, such as text summarization, code generation (SQL), and RAG.

We offer freedom of choice

• With us, you'd have a cafeteria benefits system where you can choose which benefits would fit your individual needs.

And, of course, a standard pack of benefits as well

• Health insurance, fully covered 10 working days of sick leave per year, 5 additional day-offs per year, English and other languages compensation, quartile, and annual bonuses, corporate events, gifts, also food (yummy!) — you can find snacks in our worldwide working spaces and breakfasts & lunches in the offices.