Freelance AI Engineer

About this role

Join a dynamic project supporting a leading European AI company in building and maintaining advanced large language model (LLM) inference platforms for enterprise and government clients. This role focuses on ensuring the reliability, scalability, and performance of LLM inference services, with a strong emphasis on Kubernetes-based orchestration and modern cloud infrastructure. You will collaborate with cross-functional teams to integrate, operate, and optimize LLM inference APIs, playing a key part in the delivery of robust AI solutions at scale.


Responsibilities

• Lead the integration and orchestration of LLM inference APIs within production environments
• Manage and optimize Kubernetes clusters, Helm charts, and ArgoCD pipelines for AI workloads
• Ensure high availability, reliability, and performance of inference services across multiple deployments
• Collaborate with backend, platform, and infrastructure teams to deliver seamless AI platform operations
• Implement and maintain observability, monitoring, and alerting solutions for production systems
• Drive continuous improvement in CI/CD processes and cloud infrastructure for AI applications
• Troubleshoot and resolve issues related to LLM inference, scaling, and platform reliability

Skills And Requirements

• Proven experience with Kubernetes, Helm, and ArgoCD in production environments
• Strong proficiency in Python for automation, scripting, and API integration
• Solid understanding of LLM fundamentals, inference APIs, and generative AI platforms
• Hands-on experience with cloud infrastructure (AWS, GCP, or Azure) and CI/CD pipelines
• Familiarity with observability tools (e.g., Prometheus, Grafana, ELK stack) for monitoring and alerting
• Ability to work independently and collaboratively in a distributed, fast-paced team
• Excellent problem-solving skills and attention to detail
• Strong communication skills in English
• Availability for a full-time contract position

About Twine
Twine is...