Inference Stack Engineer (M/K)

Experis ManpowerGroup Sp. z o.o.; Województwo pomorskie; Hybrid; PLN 180,000 - 260,000; Full time

Benefits offered by this job

Medical care

Job summary

Experis ManpowerGroup Sp. z o.o. is seeking an experienced Inference Stack Engineer to own runtime orchestration, graph compilation, and system integration. You will directly influence latency, efficiency, and scalability through architectural decisions.

The role demands hands-on engineering with a focus on performance-critical AI workloads, GPU/accelerator-based systems, and Linux environments, in a permanent employment setting in Poland.

Qualifications

• Bachelor's or higher in CS, EE, or related field.
• 5+ years in AI infrastructure, distributed or performance-critical backends.
• Proficiency in Python and C++.
• Hands-on experience with AI frameworks.
• Experience optimizing AI workloads performance.
• Familiarity with GPU/accelerator-based systems and Linux environments.
• Strong debugging and performance analysis across system layers.
• Ability to design end-to-end systems and drive architecture decisions.

Responsibilities

• Architect and implement runtime orchestration and system integration.
• Design and optimize performance-critical AI infrastructure.
• Guide architectural decisions impacting latency and scalability.

Skills

Python

C++

AI workloads

Performance analysis

Debugging

End-to-end system design

Education

BSc or higher in Computer Science or related field

Tools

AI frameworks

GPU/Accelerator systems

Linux environments

Job description

For our client we are looking for a candidate for the position of Inference Stack Engineer.

About the job:

We are seeking experienced software engineers with strong technical ownership, a deep understanding of performance-critical systems, and the ability to design and optimize complex infrastructure from first principles. This is a hands-on engineering role focused on runtime orchestration, graph compilation, and system integration - where your architectural decisions will directly influence the system's latency, efficiency, and scalability.

Required qualifications:

• BSc or higher in Computer Science, Electrical Engineering, or a related field
• 5+ years of experience in AI infrastructure, distributed systems, or performance-critical backend systems
• Strong proficiency in Python and C++
• Hands-on experience with AI frameworks
• Experience optimizing AI workloads performance
• Familiarity with GPU or accelerator-based systems and Linux environments
• Strong debugging and performance analysis skills across system layers
• Ability to design systems end-to-end and drive architectural decisions

Benefits:

• Medical care

The offer applies to permanent work.