🛠 Tech Stack

💼 About This Role

You'll design and build product features integrating with LLMs in production, working with clinicians and hospitals to provide clinically safe and reliable AI. You'll contribute to approaches for validating AI output quality in multilingual contexts and help build the AI doctor product.

🎯 What You'll Do

• Design and build product features integrating with LLMs in production
• Build defensively against hallucinations, output instability, and distribution shift
• Contribute to approaches for validating AI output quality in multilingual contexts
• Implement architectures and enhancements proposed by the AI research team

📋 Requirements

• Production experience building systems integrating with LLMs beyond API integration
• Strong intuition for failure modes of non-deterministic systems (output validation, fallback strategies, confidence thresholds, human-in-the-loop design)
• Ability to reason about AI quality in adversarial or ambiguous conditions
• Familiarity with prompt engineering, RAG, fine-tuning, or LLM evaluation frameworks

✨ Nice to Have

• Experience in clinical AI or high-stakes AI domains
• Exposure to AI safety concepts applied in production
• Contributed to internal AI evaluation or red-teaming exercises

🎁 Benefits & Perks

• 🏖️ 28 days holiday plus bank holidays
• 💻 Latest MacBook and equipment
• 🏢 Office-first culture at Holborn Town Hall with hybrid flexibility
• 🏥 Chance to genuinely transform healthcare

📨 Hiring Process

Estimated timeline: 3-5 weeks · AI estimate

1. 1Recruiter Screen· 30 min
2. 2Technical Interview· 60 min
3. 3System Design Interview· 60 min
4. 4On-site Interview· 120 min