Multimodal Inference & Serving Engineer

Axiōma Search; Greater London; On-site; GBP 90,000 - 120,000; Full time

Job summary

Axiōma Search is building a state-of-the-art multimodal agent inference stack in production, spanning from engine layers to serving architecture. You will help design and operate systems for low latency, high throughput, and cost efficiency while collaborating with research and engineering teams.

The role focuses on research-driven production ML and scalable infrastructure, with exposure to modern transformers and multimodal architectures in a fast-paced, VC-backed setting.

Qualifications

• Strong software engineering fundamentals with production experience.
• Proficient in Python and at least one systems language (Rust, C++, or Go).
• Hands-on experience with PyTorch or JAX in an industry setting.
• Experience with inference frameworks: vLLM, SGLang, TensorRT-LLM.
• Solid distributed systems and production ML infrastructure experience.
• Knowledge of modern ML including transformers and multimodal architectures.

Responsibilities

• Build and operate the inference stack serving multimodal agentic models in production.
• Improve latency, throughput, and cost across the serving stack.
• Research and implement inference techniques tailored to agent workloads.
• Co-design with the models team on training-time decisions that affect inference behaviour.
• Evaluate inference frameworks and hardware platforms and feed findings back into roadmap decisions.
• Stay current with advances in inference, model serving, and accelerator technology.

Skills

Python

Rust

C++

Go

PyTorch

JAX

Distributed systems

Multimodal ML

Tools

vLLM

SGLang

TensorRT-LLM

CUDA

Job description

Axiōma Search is building a state-of-the-art multimodal agent inference stack in production, spanning from engine layers to serving architecture. You will help design and operate systems for low latency, high throughput, and cost efficiency while collaborating with research and engineering teams.

The role focuses on research-driven production ML and scalable infrastructure, with exposure to modern transformers and multimodal architectures in a fast-paced, VC-backed setting.