Senior AI Software Engineer - Python, LLM Evaluation & Recs

Jobtailor; Greater London; On-site; GBP 80,000 - 110,000; Full time

Job summary

Jobtailor is seeking an experienced Python AI engineer to build and evolve AI-powered services for scalable, customer-facing experiences. You will design evaluation frameworks for AI/LLM systems and drive continuous improvement of the AI Stylist using data-driven insights.

You will apply advanced techniques like LLM-as-a-Judge to assess recommendation quality and help non-deterministic AI systems achieve better relevance and outcomes.

Qualifications

• Strong Python software engineer delivering production-grade apps.
• Experience building AI-enabled products, esp. recommendation systems or conversational AI.
• Hands-on experience designing evaluation frameworks for LLMs and AI systems.
• Comfortable with probabilistic, non-deterministic systems and data-driven improvement.
• Understanding how AI differs from traditional software and how to measure success.
• Able to translate ambiguous AI challenges into scalable solutions.

Responsibilities

• Build and evolve AI-powered services using Python at scale.
• Design and implement evaluation frameworks for AI and LLM-powered systems.
• Drive continuous improvement of AI Stylist through structured evaluation and data-driven insights.
• Apply advanced techniques such as LLM-as-a-Judge to assess recommendation quality.
• Work with non-deterministic AI systems and leverage data to improve relevance and outcomes.
• Integrate AI services into broader digital platforms, APIs, and recommendation ecosystems.

Skills

Python Programming

AI Product Development

Evaluation Framework Design

Recommendation Systems

Data-Driven Improvement

AI Systems

LLM Evaluation

Probabilistic Systems

Production-Grade Apps

Customer-Facing Apps

Data Analysis

Continuous Improvement

Scalable Solutions

Evaluation Methodologies

Tools

APIs

Digital Platforms

Recommendation Ecosystems

Job description

Jobtailor is seeking an experienced Python AI engineer to build and evolve AI-powered services for scalable, customer-facing experiences. You will design evaluation frameworks for AI/LLM systems and drive continuous improvement of the AI Stylist using data-driven insights.

You will apply advanced techniques like LLM-as-a-Judge to assess recommendation quality and help non-deterministic AI systems achieve better relevance and outcomes.