Generative AI Optimization Engineer

Project

Work done for a product or program.

• Optimise attention, KV cache and mixture-of-experts execution on the accelerator.
• Tune diffusion model pipelines including UNet, VAE and scheduler steps.
• Apply quantization and sparsity specific to generative models.
• Implement long-context and multimodal model support.
• Collaborate with kernel and compiler teams on missing fused operators.
• Publish tuned reference implementations for customers.

Function

Work that keeps the discipline running: methods, tools, suppliers and people.

• Measure quality using task benchmarks after every optimisation.

Project

1. Produce and hand over the role's key deliverables
   • Optimised generative model implementations
   • Quality and performance reports
   • Reference notebooks
   • Operator gap lists
2. Support programsGeneral
   • Agree what each program needs
   • Deliver in time for milestones
3. Manage issuesGeneral
   • Track requests to closure
   • Escalate risks

Function

1. Run the functionGeneral
   • Maintain policies and processes
   • Keep records and controls
2. ImproveGeneral
   • Report performance
   • Lead improvement work