• Build and maintain scalable backend services and APIs that power the AI Configs product • Collaborate with internal stakeholders to understand real-world challenges and improve GenAI workflows • Continuously optimize the performance, reliability, and scalability of our systems • Participate in architecture and design discussions • Keep up-to-date with the latest developments in the AI field and software development best practices • Take ownership of code in production, participate in on-call rotations

• Take full ownership of end-to-end execution of major projects for our most strategic partners, working hands-on to deliver high-impact solutions. • Collaborate daily with our customer’s engineers and executives teams to ensure the best use of ElevenLabs’ technologies. • Drive real innovation by using your coding and technical skills to solve complex problems, making a real difference for our customers.

• Contribute hands-on across the full lifecycle of AI products, from prototyping new initiatives to deploying and maintaining production AI services for internal teams and external customers. • Plan, implement, and maintain end-to-end agents. This includes selecting the right models, designing prompts, setting up Model Context Protocols (MCPs) and tool integrations, running evaluations, and ensuring production health. • Operate AI-natively every day. Actively utilize AI agents (e.g., Claude Code, Cursor, Codex, custom pipelines) to plan, implement, review, and debug your work. • Contribute to the foundational platform other Belvo squads use to ship AI, focusing on agent abstractions, conversation and state storage, durable workflow orchestration, streaming interfaces, observability, and guardrails. • Stay at the forefront of the industry by testing new models, agentic frameworks, and MCP-native patterns, selecting options based on pragmatic production reliability, cost, and latency. • Instrument and monitor AI pipelines using Langfuse and Datadog to debug failed agent runs, detect regressions, and maintain production health. • Support enablement efforts that help other Belvo squads adopt AI safely through reference implementations, integration patterns, and shared tooling.

• Design and build enterprise AI applications powered by Large Language Models and Azure-native cloud services • Collaborate closely with product, UX, platform, and engineering teams to deliver secure, scalable, and reliable AI-powered applications • Develop cloud-native and serverless applications using Azure services • Implement secure authentication and authorization systems • Apply software engineering best practices including testing, CI/CD, and code reviews • Build and optimize enterprise-grade RAG architectures • Design resilient distributed systems and optimize LLM performance • Integrate AI applications with enterprise systems and ensure strong governance and security controls