Job summary
This junior machine learning engineering role focuses on developing and maintaining infrastructure for large language model (LLM) operations and serving within a central AI platform team. The position involves collaborating with senior engineers and cross-functional teams in a media organization to support AI-driven initiatives and ensure reliable, cost-efficient access to machine learning models.
Location and work setup
- Location
- Oslo
- Work setup
- On-site
Responsibilities
Contribute alongside senior engineers to extend LLM gateway capabilities by implementing automated routing, caching, guardrails, telemetry improvements, and cost attribution. Deploy and manage self-hosted LLMs on Kubernetes in cloud and on-premise environments, performing benchmarks on model performance and cost. Enhance observability and reporting tools to provide teams with usage and cost insights. Develop and maintain evaluation tests to assess gateway and model changes. Serve as a first point of contact for internal users building AI applications, creating documentation and best practices. Stay abreast of advances in AI and machine learning technologies to inform team knowledge and innovation.
Qualifications
0-2 years experience in machine learning or software engineering roles, including internships or academic projects focused on ML or AI. Master's degree in Computer Science, Artificial Intelligence, or related disciplines. Strong Python programming skills, familiarity with Docker, Kubernetes, and command line tools. Practical experience running LLMs locally and understanding of model relevance, tools, and recent releases. Clear communication skills for explaining technical concepts to non-technical stakeholders. Demonstrated curiosity and security awareness in exploring and adopting AI technologies are valued. Experience with LLM inference tools, AI gateway solutions, or media-related data types is a plus.