Artificial Intelligence à Grande-Bretagne

Senior Backend Engineer (Application & AI Orchestration). We are seeking a deeply technical and security-minded Senior Backend Engineer to join a newly-founded, high-impact AI joint venture. Backed by five of the world's leading telecommunications giants, our mission is to restore trust in global voice communication. Our mission is to restore trust in voice communication by building a network-native intelligence layer to stop fraud and create a new category of secure, AI-powered user experiences. We are a Phase 2 company, meaning we are building the foundational engineering team that will define our culture and our success.

This role is the Core Logic Owner for our flagship AI experience: the Personal Welcome Manager. While our Security Shield product leverages unique, pre-call telco data to provide sub-500ms trust indicators, the Welcome Manager is our AI innovation showcase and primary monetization driver. This product features an AI agent that screens unknown callers as they ring, provides a live transcript, and allows for mid-call user intervention.

As the Senior Backend Engineer for Application & AI Orchestration, your central challenge will be solving the cumulative latency puzzle. You will be singularly responsible for orchestrating a best-in-class, buy, don’t build AI stack (STT - LLM - TTS) to deliver a seamless, natural, and responsive voice-to-voice (V2V) experience, targeting a sub-1000ms latency from the moment a caller stops speaking to the moment our AI begins its response. You won’t just be integrating APIs; you will be architecting the Real Time, high-throughput nervous system of our core AI product.

• Own the end-to-end Back End architecture for the Personal Welcome Manager, our flagship conversational AI product.
• Design, build, and optimize the core AI orchestration pipeline (STT - LLM - TTS) to meet our 1000ms V2V latency target.
• Serve as the technical lead for our "Buy, Don’t Build" AI strategy, integrating, managing, and evaluating third-party AI services from providers like Vapi, Deepgram, and Cartesia.
• Implement the core application logic for all Welcome Manager features, including intent-capture, post-call summarization with entity extraction, and error handling.

• Design, build, and scale the mission-critical, high-availability RESTful APIs that serve our mobile clients (Android-first).
• Architect and manage the Real Time streaming data flows (audio and text) required for the live transcription feature, utilizing technologies like WebSocket.
• Implement the Back End logic for user-facing features, such as mid-call intervention (allowing a user to accept a call during pre-screening).

• Collaborate on the design of our cloud-native, microservices-based architecture to ensure all application services are scalable, resilient, and cost-efficient.
• Work with the Platform & Security engineer to ensure all services adhere to our mandatory Zero Trust security architecture and protect sensitive user data.
• Implement comprehensive monitoring, logging, and alerting for the entire AI pipeline, with a focus on our key latency (V2V), quality, and cost metrics.

• Partner closely with the Senior Android Engineers to define robust API contracts and ensure a seamless, low-latency experience for the live transcript and mid-call intervention features.
• Collaborate with the Senior Backend Engineer (Telco Integration) to consume and orchestrate the proprietary network signals that power our Security Shield.
• Work with the Product Manager and UX/UI Designer to translate complex product requirements and the 1000ms UX flow into a concrete technical reality.
• Collaborate with the DevOps Engineer on CI/CD pipelines, Kubernetes-based service deployment, and infrastructure scaling.

• Bachelor's degree in Computer Science or a related technical field, or equivalent practical experience.
• 7+ years of hands-on experience in Back End development, building and maintaining high-availability, high-throughput systems in production.

• Expert-level proficiency and at least 5 years of production experience with Go (Golang). This role is centered on Go, and we require deep experience with its concurrency patterns and performance tuning.
• Strong, proven experience designing, building, and scaling high-availability RESTful APIs for mobile or web clients.
• Deep experience with distributed systems, microservices architecture, and event-driven patterns.
• Demonstrated experience with Real Time applications and data streaming technologies (eg, WebSockets, gRPC, Kafka).
• Experience integrating third-party AI/ML APIs (eg, LLMs, STT/TTS, or other complex services) into production systems.
• Experience with containerization (Docker, Kubernetes) and deploying/managing services on a major cloud platform (AWS, GCP, or Azure).

This is a permanent position with hybrid working of two days a week in the central London office and the rest WFH. The salary is very much Dependent on experience with a guide between £110k-£140K basic + package.