Inference Engineer

Quick Facts

• Location (office): Gdańsk
• Employment: Employment contract directly with the client (long-term)

Description

Join a team building AI systems with extreme performance requirements, combining low-level software with modern hardware architecture. In this practical engineering role, you will handle runtime orchestration, compile AI graphs, and integrate systems—where your architectural decisions directly impact latency, performance, and scalability.

Requirements

• Minimum 5 years of experience in AI infrastructure, distributed systems, or high-performance backend systems
• Very strong Python and C++ skills
• Practical experience with AI frameworks
• Experience optimizing performance for AI workloads
• Knowledge of GPU (or other accelerator) systems and Linux environments
• Strong debugging and performance analysis skills across multiple system layers
• Ability to design end-to-end systems and take/implement architectural decisions
• Higher technical education
• English at least B2+ / C1