ML Engineer: Production-Ready AI on Specialized Hardware

QuTwo; Helsinki; On-site; EUR 90,000 - 125,000; Full time

Job summary

QuTwo, a European AI lab for the quantum era, seeks an ML Engineer in Helsinki to bridge research and production. You will take models from researchers and clients and make them run within real memory, latency and hardware limits, deployed in client environments and in QuTwo OS.

You will join a small team that cares about every millisecond and megabyte, collaborating with researchers, engineers, and client teams in a fast-moving environment to bring research into production.

Qualifications

• Experience applying quantisation, pruning and distillation; recover accuracy via fine-tuning.
• Profiling to locate memory/bandwidth hotspots and deriving optimization steps.
• Hardware-aware optimizations for GPUs/NPUs/TPUs; understanding trade-offs.
• Familiar with open-weight model families and tooling.
• Domain adaptation scaffolding to adapt models to specific tasks.

Responsibilities

• Port models from research to production within memory and latency constraints.
• Collaborate with researchers, engineers and clients to deploy in QuTwo OS and client environments.
• Profile and optimize models across hardware stacks (GPUs, NPUs, TPUs) for efficient inference.

Skills

Model compression

Profiling

Hardware-aware optimisation

Open-weight models

Domain adaptation harnesses

Python and C/C++

Industry experience

Comfort with change

Job description

QuTwo, a European AI lab for the quantum era, seeks an ML Engineer in Helsinki to bridge research and production. You will take models from researchers and clients and make them run within real memory, latency and hardware limits, deployed in client environments and in QuTwo OS.

You will join a small team that cares about every millisecond and megabyte, collaborating with researchers, engineers, and client teams in a fast-moving environment to bring research into production.