£450 Per day
Inside
Hybrid
London
Summary: The Python Senior Engineer role involves joining the Recommendations team to enhance the AI Stylist experience, which integrates conversational interfaces with recommendation capabilities. The position focuses on engineering and AI, aiming to improve system relevance, quality, and reliability in a customer-facing environment. Collaboration with engineers, data scientists, and product stakeholders is essential for system evolution and growth. The role requires building AI-powered services and implementing evaluation frameworks for LLM-based systems.
Key Responsibilities:
- Building and evolving AI-powered services using Python
- Designing and implementing evaluation frameworks for LLM-based systems
- Improving output quality through structured evals rather than purely code changes
- Applying techniques such as LLM-as-a-Judge to assess response and recommendation quality
- Working with non-deterministic systems and iterating based on real-world behaviour
- Integrating AI services into a broader platform and API ecosystem
- Contributing to production readiness including reliability, observability, and performance
- Partnering with data scientists on prompts, model usage, and evaluation strategies
Key Skills:
- Strong Python engineering experience in production environments
- Experience building AI-enabled applications, particularly in recommendation or conversational systems
- Hands-on experience with evaluation frameworks for LLM or AI systems
- Clear understanding of how AI systems differ from traditional deterministic systems
- Ability to design meaningful evals and improve system quality over time
- Experience working in cross-functional teams with engineering, data, and product
Salary (Rate): £450/day
City: London
Country: United Kingdom
Working Arrangements: hybrid
IR35 Status: inside IR35
Seniority Level: Senior
Industry: IT
Python Senior Engineer - 12 Months - London - Hybrid
You will join the Recommendations team, contributing to the AI Stylist experience, an AI-powered product that combines conversational interfaces with recommendation capabilities.
The work sits at the intersection of engineering and AI, focused on improving relevance, quality, and reliability in a live, customer-facing system.
You will collaborate closely with engineers, data scientists, and product stakeholders to evolve the system and support its rapid growth
Your responsibilities:
- Building and evolving AI-powered services using Python
- Designing and implementing evaluation frameworks for LLM-based systems
- Improving output quality through structured evals rather than purely code changes
- Applying techniques such as LLM-as-a-Judge to assess response and recommendation quality
- Working with non-deterministic systems and iterating based on real-world behaviour
- Integrating AI services into a broader platform and API ecosystem
- Contributing to production readiness including reliability, observability, and performance
- Partnering with data scientists on prompts, model usage, and evaluation strategies
Essential skills/knowledge/experience:
- Strong Python engineering experience in production environments
- Experience building AI-enabled applications, particularly in recommendation or conversational systems
- Hands-on experience with evaluation frameworks for LLM or AI systems
- Clear understanding of how AI systems differ from traditional deterministic systems
- Ability to design meaningful evals and improve system quality over time
- Experience working in cross-functional teams with engineering, data, and product
Desirable skills/knowledge/experience:
- Experience with Azure AI services or similar platforms
- Familiarity with OpenAI or similar SDKs
- Exposure to infrastructure and distributed systems
- Experience with tools such as Terraform or Kafka
The Offer
- Day Rate: £450/day (inside IR35)
- Length: 12 Months (Extenstion Potential)
- Mode: Hybrid (2x p/w in London)
- Start: ASAP