Lead AI Product Engineer

This is a fully remote position, open to applicants in United Kingdom.

📋 Description

• Take ownership of solutions from the initial discovery and architecture phases through to implementation, phased testing, deployment, monitoring, and production support.

• Integrate AI capabilities into practical applications and workflows, which includes model and service integration, grounding or retrieval patterns, structured outputs, orchestration, guardrails, and fallback behavior.

• Develop user-friendly web experiences, robust APIs and services, and establish reliable connections between application, AI, and data layers.

• Design shared components, templates, reference architectures, deployment patterns, and standards for reuse across various initiatives.

• Define testing protocols throughout the development and deployment phases.

• Implement automated software tests and establish repeatable evaluations of AI quality, reliability, latency, and failure modes.

• Instrument applications for tracing AI, data, integration, and application behavior.

• Analyze issues across upstream and downstream dependencies and implement sustainable fixes.

• Incorporate authentication, authorization, secrets management, data protection, auditability, compliance controls, and lineage into solution design.

• Measure and enhance operating costs, token consumption, model selection, retrieval strategy, caching, latency, and infrastructure utilization.

• Report on the economics of operating each solution.

• Collaborate with UI/UX and business stakeholders to enhance user outcomes and adoption rates.

• Share ideas, review designs and code, provide specialized knowledge, and lead challenges that align with technical strengths.

⛳️ Requirements

• Extensive professional experience in software engineering, including taking ownership of production systems and making technical decisions at a Lead or Principal level.

• Hands-on experience in delivering AI-enabled products or application features that operate in production and support ongoing business workflows.

• Strong full-stack development skills: modern JavaScript/TypeScript, React or Next.js, API and service development, and integration with enterprise data platforms.

• Robust backend engineering experience in C#/.NET or a similar enterprise stack.

• Solid understanding of distributed systems, asynchronous processing, and integration patterns.

• Extensive experience with Azure or another major cloud platform, including secure networking, identity management, secrets, serverless or containerized services, CI/CD, infrastructure as code, and production telemetry.

• Practical knowledge of LLM application architecture, including model APIs, retrieval and grounding, prompt and context design, structured output, evaluation, monitoring, and responsible failure handling.

• Ability to articulate trade-offs between quality, user experience, latency, security, maintainability, and cost.

• Persistent, low-ego problem-solving approach; capable of navigating ambiguity, seeking expertise when necessary, and remaining accountable until issues are resolved.

• Excellent written and verbal communication skills with engineers, product partners, business stakeholders, and support teams.

• Nice to have: Familiarity with Azure OpenAI or similar managed model services, Azure AI capabilities, and practical experience with leading model providers.

• Nice to have: Experience with Application Insights, OpenTelemetry, distributed tracing, AI-specific observability, or evaluation tools.

• Nice to have: Experience with Snowflake or similar cloud data platforms.

• Nice to have: Knowledge of enterprise design systems, accessibility, user research, and collaboration with UI/UX teams.

• Nice to have: Experience in regulated or data-sensitive environments.

• Nice to have: Working proficiency in Python for AI services, evaluation, data processing, or automation.

🏝️ Benefits

• No specific benefits or compensation extras stated in the posting.