Research Engineer, Model Inference & Serving - London

Role

The role involves building and operating the inference stack for multimodal agentic models while improving latency, throughput, and cost. Candidates must have strong software engineering skills, proficiency in Python and a systems language, and experience with deep learning frameworks and distributed systems.

Location: Hybrid London
Employment: unspecified
Work pattern: hybrid
Seniority: unspecified

APPLY ON THE EMPLOYER’S SITE ↗

Source and currency

This vacancy came from the organization’s official Ashby feed. Source update: 2026-04-10T07:14:15.036+00:00. Check the employer’s page for the complete description, current availability and application terms.

• jobs.ashbyhq.com/hcompany/8ef0a8b6-40e1-40da-a337-4454ad39b66a ↗

H Company RESEARCH PROFILE ↗