Codurance
Senior GenAI Full-Stack Engineer - Brazil
About this role
Description: Design and extend production-grade LLM applications and workflows using NestJS, XState v5, and OpenAI SDK. Build and maintain conversation-machine substrate and AI systems for Epic Support Assistant and Agent Support Assistant. Integrate with MCP servers for tool-use and agentic behaviors. Evaluate and tune models across various providers, managing model selection decisions. Troubleshoot production LLM issues and build resilience mechanisms. Instrument and tune model quality using various evaluation and telemetry tools. Manage async workloads and caching with Redis and PostgreSQL persistence. Requirements: Proven experience with production LLM-powered systems like chatbots or AI assistants. Strong TypeScript/Node.js engineering skills with strict-mode fluency. Experience in prompt engineering, RAG pipelines, and AI feature shipping. Fullstack development capability across APIs, UIs, databases, and infrastructure. Ability to evaluate tradeoffs in model quality, latency, and cost. Troubleshooting skills across prompts, retrieval pipelines, and application code. Familiarity with state machine modeling and async patterns. Strong testing culture with unit, integration, and contract tests. Experience working in a monorepo with interconnected services. Benefits: Opportunity to work on cutting-edge AI technologies and applications. Collaborative environment with a focus on innovation and quality.