Senior Inference Engineer - AI APIs

AssemblyAI; United Kingdom; On-site; GBP 120,000 - 145,000; Full time

Job summary

AssemblyAI is seeking a Software Engineer in the United Kingdom to help turn cutting-edge AI research into robust, production-grade APIs and scalable inference infrastructure. You will sit on a fast-paced engineering team bridging research and Applied groups, turning models into reliable production features.

You will design and ship customer-facing APIs, scale inference systems, and collaborate with researchers to productionize new techniques.

Qualifications

• Strong backend engineering experience building and supporting ML infrastructure and customer-facing APIs in production.
• Comfort operating with ambiguity and aligning research timelines with product timelines.
• Genuine curiosity about AI/ML to inform engineering decisions.
• Strong collaboration skills across researchers, applied engineers, and customers.

Responsibilities

• Design and ship customer-facing APIs exposing new model capabilities from prototype to launch.
• Scale inference infrastructure to support 1M+ API users.
• Productionize new research techniques in latency, reliability, and ergonomics.
• Collaborate with customers and Applied teams to feed feedback into product direction.
• Contribute across the stack: backend services, inference infra, SDKs, internal tooling.

Skills

Backend engineering

ML infrastructure

APIs

Production systems

Job description

AssemblyAI is seeking a Software Engineer in the United Kingdom to help turn cutting-edge AI research into robust, production-grade APIs and scalable inference infrastructure. You will sit on a fast-paced engineering team bridging research and Applied groups, turning models into reliable production features.

You will design and ship customer-facing APIs, scale inference systems, and collaborate with researchers to productionize new techniques.