Hardware-Aware AI Model Optimisation Engineer

Callosum Technologies Ltd.

Greater London

Presencial

GBP 120.000 - 170.000

Jornada completa

Hace 9 días

Una candidatura completa en un minuto

Currículum y carta de presentación personalizados, listos para enviar.

Supera los filtros ATS

Ventajas ofrecidas por este puesto de trabajo

Equity & Ownership
Private healthcare
Visa sponsorship and relocation
London office

Descripción de la vacante

Callosum Technologies Ltd. is developing infrastructure that unifies heterogeneous compute across the full stack. We aim to tailor inference to each workload by co‑evolving models and silicon, enabling cost and latency advantages while maintaining quality.

Based in London, we hire engineers who thrive on uncharted territory and scale intelligent systems with cutting‑edge accelerator architectures. The role focuses on adapting model architectures and inference algorithms to new hardware

Formación

  • Deep understanding of modern LLM architectures and attention mechanisms.
  • Experience in model architecture research, efficient inference, or hardware‑aware ML.
  • Familiarity with mixture‑of‑experts, diffusion, JEPA, or alternative attention mechanisms.
  • Strong intuition for interactions between model capability, numerical behaviour, memory, and execution efficiency.
  • Experience designing rigorous experiments to assess model quality and efficiency.

Responsabilidades

  • Develop hardware‑aware transformations that adapt models to different accelerator architectures and execution environments.
  • Explore numerical, structural, and memory‑related optimisations to create model variants with different capability, latency, and cost trade‑offs.
  • Investigate new inference algorithms, including speculative decoding, to exploit heterogeneous resources.
  • Develop automated methods for discovering, characterising, and optimising hardware‑specialised model variants.
  • Build evaluation methods to measure model quality and establish trade‑offs introduced by hardware‑aware adaptations.

Conocimientos

LLM architectures
Model architecture research
Efficient inference
Hardware-aware ML
Attention mechanisms

Descripción del empleo

Callosum Technologies Ltd. is developing infrastructure that unifies heterogeneous compute across the full stack. We aim to tailor inference to each workload by co‑evolving models and silicon, enabling cost and latency advantages while maintaining quality.

Based in London, we hire engineers who thrive on uncharted territory and scale intelligent systems with cutting‑edge accelerator architectures. The role focuses on adapting model architectures and inference algorithms to new hardware

Consigue la evaluación confidencial y gratuita de tu currículum.

o arrastra y suelta tu archivo aquí

Similar jobs

Puestos de trabajo similares que vale la pena comparar

Hardware-Aware Model Optimisation Engineer – London Equity
Hardware-Aware Model Optimisation Engineer – London Equity

Abundant Code • Greater London

Presencial
GBP 120.000 - 180.000
Equity & Ownership
Private healthcare
Visa sponsorship
+2
Hardware‑Aware AI Model Optimisation Engineer
Hardware‑Aware AI Model Optimisation Engineer

Callosum • Greater London

Presencial
GBP 110.000 - 160.000
Competitive salary
Equity & ownership
Private healthcare
+2
Hardware-Aware ML Optimization Specialist
Hardware-Aware ML Optimization Specialist

present of AI • Greater London

Presencial
GBP 90.000 - 130.000
Hardware-Aware Model Optimisation - Member of Technical Staff
Hardware-Aware Model Optimisation - Member of Technical Staff

Callosum • Greater London

Presencial
GBP 110.000 - 160.000
Competitive salary
Equity & ownership
Private healthcare
+2
Hardware-Aware Model Optimisation - Member of Technical Staff
Hardware-Aware Model Optimisation - Member of Technical Staff

Callosum Technologies Ltd. • Greater London

Presencial
GBP 120.000 - 170.000
Equity & Ownership
Private healthcare
Visa sponsorship and relocation
+1
Hardware-Aware Model Optimisation - Member of Technical Staff
Hardware-Aware Model Optimisation - Member of Technical Staff

present of AI • Greater London

Presencial
GBP 90.000 - 130.000
Hardware-Aware Model Optimisation – Member of Technical Staff Callosum
Hardware-Aware Model Optimisation – Member of Technical Staff Callosum

Abundant Code • Greater London

Presencial
GBP 120.000 - 180.000
Equity & Ownership
Private healthcare
Visa sponsorship
+2
Senior AI Infrastructure Simulation Scientist
Senior AI Infrastructure Simulation Scientist

Abundant Code • Greater London

Presencial
GBP 90.000 - 130.000
Competitive salary
Equity & Ownership
Private healthcare
+1
Staff AI Systems Engineer: Automated Optimization
Staff AI Systems Engineer: Automated Optimization

Callosum • Greater London

Presencial
GBP 120.000 - 180.000
Competitive Salary
Equity & Ownership
Private healthcare
+2
Inference Performance & Deployment - Member of Technical Staff
Inference Performance & Deployment - Member of Technical Staff

Callosum • Greater London

Presencial
GBP 90.000 - 130.000
Equity & Ownership
Private healthcare
Visa sponsorship and relocation
+1