Research Engineer, Multimodal Inference & Serving

hcompany; Greater London; Hybrid; GBP 90,000 - 130,000; Full time

Benefits offered by this job

Competitive salary

Hybrid work model

Career development

Job summary

H is seeking a Research Engineer to advance inference and serving for multimodal agentic AI. You will build and operate the production stack, optimizing latency and cost while collaborating with the Models team and cross-functional partners in a hybrid Paris/London setting.

You will apply Python and systems programming, work with PyTorch/JAX, and contribute to scalable ML infrastructure across cloud environments. This role offers growth, a competitive salary, and travel between offices.

Qualifications

• Strong software engineering track record.
• Proficient in Python and at least one systems language such as Rust, C++, or Go.
• Hands-on experience with deep learning frameworks (PyTorch, JAX).
• Solid distributed systems fundamentals.
• Experience with production ML infrastructure (Kubernetes).
• Working knowledge of modern ML including transformers and multimodal architectures.
• Advanced degree with research output or publications in AI/systems venues.

Responsibilities

• Build and operate the inference stack that serves H's multimodal agentic models.
• Improve latency, throughput, and cost of model serving across the stack.
• Research and implement inference techniques tailored to agent workloads.
• Co-design with the Models team on training-time decisions that affect inference.
• Collaborate with cross-functional teams to integrate inference into agentic AI products.
• Evaluate inference, serving, and hardware platforms, and communicate findings to stakeholders.
• Stay current with advancements in inference, model serving, and accelerator technology.

Skills

Python

Rust

C++

Go

PyTorch

JAX

Distributed systems

Kubernetes

Cloud infra

Transformers

Multimodal models

Education

Advanced degree

Tools

vLLM

SGLang

TensorRT-LLM

CUDA

Triton

llama.cpp

MLX

ONNX Runtime

Job description

H is seeking a Research Engineer to advance inference and serving for multimodal agentic AI. You will build and operate the production stack, optimizing latency and cost while collaborating with the Models team and cross-functional partners in a hybrid Paris/London setting.

You will apply Python and systems programming, work with PyTorch/JAX, and contribute to scalable ML infrastructure across cloud environments. This role offers growth, a competitive salary, and travel between offices.