• Own the architecture for DHI as a platform, making high-leverage decisions that define how images and Helm charts are authored, secured, distributed, and evolved across the entire catalogue and across Docker's broader product surface. • Define and drive multi-quarter technical roadmaps for the container hardening domain, balancing upstream velocity, supply chain security posture, customer compliance requirements, and long-term catalogue scalability. • Identify systemic patterns from customer, operational, and upstream signals and translate them into architectural changes that span the catalogue, not just individual images or charts. • Build alignment across teams and executives on technical strategy, tradeoffs, and sequencing, including product, security, infrastructure, and customer-facing functions. • Represent Docker as a trusted technical voice in escalations, key enterprise customer engagements, and upstream OSS communities on issues that shape the future of secure container delivery. • Set conventions and standards at scale, defining the patterns others build within for image definition, Helm chart adaptation, hardening strategy, and supply chain tooling (Sigstore, SBOM, SLSA), and evolving those standards as the ecosystem changes. • Drive the hardest, most ambiguous packaging problems where the right answer requires reasoning across upstream dynamics, security tradeoffs, multi-arch constraints, and customer impact simultaneously. • Shape the integration test infrastructure and developer tooling strategy so that DHI's engineering platform scales with the catalogue and raises quality across the team. • Mentor and raise the technical ceiling for staff and senior engineers across the org, through review, design, and well-chosen architectural decisions that create durable leverage. • Take part in the paid on-call rotation; respond to incidents, debug production issues, and drive systemic improvements in reliability.

• 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

• Help build and scale PAD, CTA’s flagship data infrastructure platform • Perform meaningful engineering work on products enabling campaigns, nonprofits, advocacy groups, and movement partners to use data effectively • Build and maintain data products and pipelines using industry-standard tools and languages • Contribute to the culture and success of the organization • Collaborate with a team on a wide-ranging codebase including AI toolkits • Bring a security-first mindset to development • Participate in deployment and operations in the cloud