• Translate ambiguous stakeholder requirements into structured solutions, user flows, and deliverables • Design system architecture, making decisions around scalability, maintainability, and security • Build and deliver end-to-end features across frontend and backend with full ownership • Rapidly prototype AI-enabled solutions and evolve them into production-ready systems • Improve and scale an existing Python-based application, addressing backlog, performance, and UX gaps • Define and implement UX flows and usability improvements (not visual design, but user journeys) • Integrate with APIs, including AI-driven services, and design robust data flows • Apply secure development practices and ensure systems are reliable and maintainable • Balance speed of delivery with long-term engineering quality and structure • Contribute to and elevate engineering practices (architecture, SDLC, testing) through hands-on work • Collaborate with stakeholders and team members while operating with a high degree of independence

• Translate ambiguous stakeholder requirements into structured solutions, user flows, and deliverables • Design system architecture, making decisions around scalability, maintainability, and security • Build and deliver end-to-end features across frontend and backend with full ownership • Rapidly prototype AI-enabled solutions and evolve them into production-ready systems • Improve and scale an existing Python-based application, addressing backlog, performance, and UX gaps • Define and implement UX flows and usability improvements (not visual design, but user journeys) • Integrate with APIs, including AI-driven services, and design robust data flows • Apply secure development practices and ensure systems are reliable and maintainable • Balance speed of delivery with long-term engineering quality and structure • Contribute to and elevate engineering practices (architecture, SDLC, testing) through hands-on work • Collaborate with stakeholders and team members while operating with a high degree of independence

Role Description Kimchi is the AI platform inside CAST AI. We started by helping companies run LLMs on their own Kubernetes clusters - now we're building the execution layer where agents do real work. What you'll build: - The ratchet: Engineering solutions to prevent agent mistakes. - Long-horizon execution: Spec-driven autonomy, automatic replanning, and crash recovery. - Planner/executor splits: Using different models for planning, executing, and evaluating. - The harness surface: CLI, TUI, MCP integration, and telemetry. - Memory and context: Managing state and context across sessions. Qualifications - Experience using AI coding agents in real work scenarios. - Strong TypeScript or Go skills in production. - Ability to think in harness terms and diagnose context issues. - Experience driving features end-to-end. Requirements - Build and evolve the agent harness. - Own long-horizon execution and completion metrics. - Architect planner/executor/evaluator pipelines. - Manage agent memory and context. - Own the harness surface and integrations. Benefits - Competitive salary (€6,500 - €9,000 gross, depending on experience). - Flexible, remote-first global environment. - Collaboration with a global team of cloud experts. - Equity options. - Fast-paced workflow with quick feedback. - 10% of work time on personal projects or self-improvement. - Learning budget for professional and personal development. - Annual hackathon to spark new ideas. - Team-building budget and company events. - Equipment budget for necessary tools. - Extra days off for work-life balance.

• Own the design and governance of GLOBO’s modern data stack • Architect and maintain data pipelines using Fivetran for ingestion, dbt for transformation, and Snowflake for warehousing and analytics • Define data modeling standards, ensure data quality and integrity, and establish governance practices across the organization • Manage, mentor, and grow a team of 3–5 AI and data engineers • Set team priorities aligned with company objectives, conduct regular 1:1s and performance reviews, and foster a culture of engineering excellence • Lead the design and development of AI-powered features within the GLOBO platform • Build and deploy LLM integrations (AWS Bedrock, Anthropic Claude) that solve business problems • Monitor and optimize performance and cost across data and AI services.