Senior Real-Time ML Inference Engineer

BITKRAFT Ventures; United Kingdom; On-site; GBP 140,000 - 200,000; Full time

Job summary

Inworld is seeking an experienced engineer to advance real-time AI capabilities for consumer-facing applications. You will drive end-to-end ownership from research to production, containerizing models and optimizing serving pipelines for ultra-low latency on modern GPUs.

Ideal candidates combine PhD-level or equivalent practical expertise with strong C++, CUDA, and distributed systems experience, including Kubernetes and Ray, to scale high-performance inference at scale.

Qualifications

• PhD in CS, Physics, Math, or equivalent practical experience.
• Proven experience building backend or ML systems.
• Experience with distributed systems and high-performance computing.

Responsibilities

• Own models from research through containerization and serving.
• Optimize inference pipelines for latency and throughput.
• Collaborate across teams to deploy ML systems in production.

Skills

Inference Optimization

Model Acceleration

High-Performance Systems

Distributed Systems

Open Source / Public Work

End-to-end Ownership

PhD or Equivalent

Education

PhD in CS, Physics, Math

Tools

C++

CUDA

Rust

Python

Kubernetes

Ray

Job description

Inworld is seeking an experienced engineer to advance real-time AI capabilities for consumer-facing applications. You will drive end-to-end ownership from research to production, containerizing models and optimizing serving pipelines for ultra-low latency on modern GPUs.

Ideal candidates combine PhD-level or equivalent practical expertise with strong C++, CUDA, and distributed systems experience, including Kubernetes and Ray, to scale high-performance inference at scale.