ML Engineer

O projekcie: For our IT industry partner, we are seeking an experienced ML/AI Engineer. You will learn the name of your future employer during the very first contact, i.e. in the initial phone conversation, and the recruitment process itself will be efficient and fast. We are looking for a hands-on ML Engineer to help us develop AI products in our portfolio. You will be building the core engine of our AIaaS platform (based on vLLM), delivering to our clients reliable platform for hight-throughput LLM serving. Your involvement does not stop there, as you will also be involved in building RAGs (LangChain, Milvus) and agentic workflows. Wymagania: Required Experience: - Proficiency in deploying and optimizing LLM inference engines in a production environment. - Ability to build and scale RAG pipelines. - Data science skills to adapt our RAG pipelines to the client’s data. - Expertise in managing production workloads on Kubernetes. - Skilled in creating complex workflows, creating and integrating different agents. Highly Desirable: - Model Fine-Tuning: experience with PEFT techniques like LoRA. - Evaluation Frameworks: you know how to measure and improve RAGs. - Open source models: familiarity with open source LLM models. - API Gateway Management: experience with Apache APISIX, including rate limiting, throttling AI inference. - GitOps: experience with ArgoCD in managing K8S deployments. Codzienne zadania: - AIaaS development: architect, develop and maintain LLM inference services. - MLOps: be responsible for the deployment lifecycle, from containerisation to monitoring model performance, token usage, and system reliability in production. - RAG: implement and optimize our RAG pipelines, make them work best with our clients data. - Agents and workflows: create LLM-based agents to help our clients automate their business processes.