**\#JoinLuby** ---------------- **Here’s what you’ll get to do:** * **Grow in a high-performance environment:** A culture where continuous development is the norm—offering autonomy and involvement in national and international projects that truly challenge your skills and accelerate your potential. * **Join a team passionate about technology:** You’ll collaborate with experienced talent in a collaborative, disruptive environment, leveraging the most advanced technologies available in the market. * **Make your mark on the world:** Our digital solutions directly impact the lives of thousands of people—and this is your chance to actively help build a more digital and connected future. * **Work remotely and flexibly:** No matter where you are, we’re ready to welcome you to our team! **Your Mission:** We’re seeking a Senior Software Engineer with strong fluency in Ruby on Rails and Vue.js to build AI features—validated and promoted before reaching any other system. You’ll be responsible for developing the orchestration harness around agents, designing RAG tools that ground clinical outputs in real patient data, and integrating real-time AI responses into the architecture—without compromising the workflow that depends on them. Working end-to-end across the stack, you’ll deliver features that feel native to the product and leave the codebase cleaner, more testable, and agent-ready. **Key Responsibilities:** * Develop end-to-end AI-native features in the CHR, spanning Rails service layers, WebSocket streaming via ActionCable, and Vue.js components rendering agent output. * Design and implement the agent tooling layer in Ruby (service objects, background jobs with Sidekiq, and ActionCable handlers), built atop the CHR’s real data model for operations such as medical record lookup, SOAP notes, billing rule checks, and lab result retrieval. * Build and maintain the real-time AI response pipeline, using ActionCable to stream agent outputs to the Vue.js frontend while handling partial responses, error states, human-in-the-loop interruptions, and controlled degradation when the LLM is slow or unavailable. * Own context engineering for CHR agents, developing the Rails context assembly layer that securely aggregates medical record data, care history, and clinical context from PostgreSQL—optimized for PHI compliance, token efficiency, and auditability. * Develop Vue.js components compatible with the A2UI pattern for AI surfaces, defining component contracts produced by agents and consumed by renderers—aligned with the CHR’s design system and clinical UX conventions. * Implement RAG tools for retrieving CHR-specific knowledge, building embedding pipelines over clinical content, designing appropriate retrieval mechanisms, and evaluating quality against clinical ground truth. * Manage token economy per delivered agent—understanding context cost, applying compression and summarization strategies on patient history, and monitoring cost-per-call as a production metric alongside latency and quality. * Instrument every AI feature for production observability—integrating ActionCable traces, Sidekiq job metrics, LLM latency, evaluation score trends, and clinical accuracy signals into the observability stack. * Uphold the OPERATE mandate—ensuring AI work does not degrade existing clinical workflows, since the CHR serves real clinicians and patients. * Register Knowledge Graph entries for each delivered feature, encoding clinical protocols, billing rules, and edge cases in machine-queryable format. * Work with international clients. **Essential Requirements:** * Bachelor’s degree in Computer Science, Software Engineering, or related field. * Strong production-level proficiency in Ruby on Rails—including multi-tenant applications, ActiveRecord query optimization, Sidekiq background job architecture, ActionCable for real-time features, and security patterns. * Fluency in Vue.js—capable of building component-driven interfaces that cleanly integrate with Rails backends, handle real-time WebSocket streams, and adhere to an existing design system. * Proven experience building AI features in production—having delivered at least one feature relied upon by real users (e.g., a RAG pipeline, agent integration, or streaming LLM response). * Prompt engineering instinct—with hands-on practice in versioned, tested, and optimized prompts—focused on token cost and latency. * Experience implementing agentic tooling—understanding function calling, tool registries, and multi-step loops at the implementation level. * Observability discipline—systematically instrumenting what you build and treating production signals as first-class engineering feedback. **What We Offer:** * **Remote Work:** Enjoy the flexibility to work from anywhere in Brazil—with full autonomy and self-organization. * **Health & Well-being:** Health and dental plans, life insurance, and Wellhub (Gympass). * **\+Education:** Discounts on FIAP courses and USP Esalq MBA programs—so you can keep learning and growing. * **Exclusive Perks:** Discounts at Multilaser stores, referral bonuses for professionals and business leads, flexible working hours, and annual bonus. ### ***Learn more about our culture, perks, and what it’s like to be a \#Luber on our*** ***Careers Page!***
João Silva
Indeed · HR
João Silva
Indeed · HR
