Engineering and infrastructure

Inference and model optimisation

Inference and model optimisation is the work of serving learned models quickly and cheaply while holding quality to an agreed standard. AI companies need it because a model that works in testing still has to run affordably, reliably and within limits in production.

More companies are moving from demos to products that real customers use all day. Serving costs and response times then shape what the business can offer. The tricky part is that speed is easy to buy if you accept worse answers. Strong candidates treat task and safety performance as a hard constraint, measure regressions carefully, and can explain what they traded away. Many come from performance engineering, ML systems or distributed services, so check they understand model behaviour, not only hardware.

Hiring now 4

Roles in this family

4 roles

Hiring nowInference Systems EngineerAn Inference Systems Engineer builds the serving engines and runtime services that run models in production. They keep latency low and cost under…Hiring nowModel Compression EngineerA Model Compression Engineer makes trained models smaller and faster to run without letting quality slip past agreed limits. For a company, that…Hiring nowInference Performance EngineerAn Inference Performance Engineer profiles how a model is served, finds where time and accelerator capacity are lost, and fixes it without hurting…Hiring nowEdge AI EngineerAn Edge AI Engineer gets learned models running on constrained devices and offline environments, within clear limits on power, memory and latency…

Where the people come from

Performance engineering, ML systems or distributed services

Not to be confused with. Latency optimisation must retain task and safety performance.

Core skills

  • Distributed systems
  • GPU programming
  • Model compression
  • Inference serving

Where it is used

  • Cross-sector AI platforms
  • Enterprise software and developer tools
  • Semiconductors and compute infrastructure

More in Engineering and infrastructure

Applied AI and machine learning engineering0 rolesDistributed training and research systems0 rolesMLOps and AI platform engineering0 rolesAI observability, reliability and FinOps0 rolesAI compilers, kernels and runtime systems0 rolesAI accelerators and hardware co-design0 rolesAI data centre networks and facilities0 rolesPrivacy-preserving and confidential AI0 roles

← All new job families

Start a search

Hiring in inference and model optimisation?

Tell us the work you need done. We find the people already doing it, whatever their job title says.