Python Inference Engineer (Fully Remote)

• Build and improve the inference layer of the Gcore Inference platform, integrating frameworks like vLLM and TensorRT-LLM.
• Bring new language and multimodal models into production, optimizing latency, throughput, and cost efficiency.
• Debug performance issues across model code, GPU execution, and Kubernetes, collaborating with cross-functional teams.

What We’re Looking For:

• 5+ years of production code experience with strong Python and PyTorch skills.
• Hands-on experience with Linux, Docker, Kubernetes, and distributed systems.
• Ability to debug complex problems across software, infrastructure, and hardware.
• Competitive compensation and flexible working hours with hybrid or remote options.
• Private medical insurance for you and your family, plus extra paid vacation and sick leave days.
• Language courses, modern offices, and team social activities.

Gcore

Gcore is a global provider of AI, cloud, network, and security infrastructure and software. They are a team of 550+ professionals with a collaborative culture and partnerships with Intel, NVIDIA, Dell, and Equinix.