Developer Experience Engineer for AI Inference

DeepCamp; City Of London; Hybrid; GBP 90,000 - 130,000; Full time

Benefits offered by this job

Equity and Ownership

Private Medical, Dental & Vision

Contributory Pension

25 Days holiday plus bank holidays

Life/Critical Illness Insurance

Job summary

Fractile is building high‑speed AI inference hardware and software. The Developer Experience team designs tools to streamline how engineers interact with the Fractile inference accelerator and its software stack.

You will identify opportunities to improve performance, design usable tools, and ensure seamless integration with an LLM engineer’s workflow, minimizing disruption while delivering measurable gains.

Qualifications

• Experience with inference frameworks such as JAX and PyTorch.
• Strong software development experience in Python, Rust, or C/C++.
• Experience profiling and optimizing CUDA, ROCm, or OpenCL code.
• Experience deploying and monitoring large‑scale LLM workloads (50B+ params).

Responsibilities

• Identify tooling opportunities to improve engineers' workflow with minimal disruption.
• Design and deliver developer tools integrated into existing LLM pipelines.
• Collaborate with inference hardware teams to optimize performance.
• Contribute to a scalable software stack for AI inference at scale.

Skills

JAX

PyTorch

Python

Rust

C/C++

CUDA/ROCm/OpenCL

LLM deployments (50B+ params)

Cross-team collaboration

Job description

Fractile is building high‑speed AI inference hardware and software. The Developer Experience team designs tools to streamline how engineers interact with the Fractile inference accelerator and its software stack.

You will identify opportunities to improve performance, design usable tools, and ensure seamless integration with an LLM engineer’s workflow, minimizing disruption while delivering measurable gains.