Production AI Engineer - Reliable LLMs, Python, Remote UK

Xist4 IT Limited.; United Kingdom; Remote; GBP 85,000 - 100,000; Full time

Benefits offered by this job

Equity

Job summary

Xist4 IT Limited. in the United Kingdom is seeking an Applied AI Engineer to ship end-to-end AI features from model behaviour to the user experience. You will design prompts, tools, memory and agent workflows and turn raw model outputs into reliable user-facing products.

You will partner with product and engineering to reduce latency and cost, improve production reliability and turn research into dependable systems for real users.

Qualifications

• Hands-on experience training, fine-tuning or deploying ML models.
• Strong foundations in ML and modern neural network architectures.
• Experience taking ML or AI systems into production, beyond experimentation.
• Production-quality Python engineering.
• Experience working with LLMs, model APIs or open models.
• Experience working across model, infrastructure and product layers.
• Experience diagnosing production ML issues and addressing root causes.

Responsibilities

• Build and ship AI features end-to-end, from model behaviour through to the user experience.
• Design and iterate on prompts, tools, memory and agent workflows.
• Turn raw model outputs into structured, reliable and predictable behaviours.
• Debug issues across models, orchestration, infrastructure and product.
• Improve latency, cost and production reliability.
• Build lightweight evaluation frameworks around real-world performance.
• Work with product and engineering to turn ambiguous problems into working systems.
• Use production signals to drive measurable improvements to models and systems.

Skills

ML model training

Production ML

Python engineering

LLMs

Model APIs

Infrastructure awareness

Root cause analysis

Tools

PyTorch

JAX

LLama/Qwen

vLLM

Job description

Xist4 IT Limited. in the United Kingdom is seeking an Applied AI Engineer to ship end-to-end AI features from model behaviour to the user experience. You will design prompts, tools, memory and agent workflows and turn raw model outputs into reliable user-facing products.

You will partner with product and engineering to reduce latency and cost, improve production reliability and turn research into dependable systems for real users.