Senior Full Stack Engineer.

Accountabilities

• Build and maintain production-grade AI agents using TypeScript, Node.js, AWS Lambda, Step Functions, DynamoDB, Amazon Bedrock, and frameworks such as Strands or LangGraph.

• Design agent workflows by defining what AI models can investigate and which actions must be controlled by deterministic code.

• Develop secure, sandboxed agent runtimes with read-only access, scoped tools, controlled file access, and appropriate budget and timeout limits.

• Evaluate AI features using benchmark datasets, production replays, calibrated evaluation models, and quality gates based on recall, precision, and false-positive rates.

• Compare models and inference effort levels before release to ensure reliable, measurable performance.

• Improve observability through structured logs, reason-coded metrics, alerts, and production troubleshooting using tools such as Splunk and VictoriaMetrics.

• Maintain Terraform infrastructure across environments while respecting tagging standards, permission boundaries, and security requirements.

• Enhance GitLab CI/CD pipelines for building, testing, deploying, and enforcing quality controls.

• Build resilient integrations that handle retries, rate limits, permanent failures, and outdated application state.

• Use AI coding assistants to accelerate development, review generated code critically, and maintain accurate context for AI-assisted workflows.

• Review AI-generated changes for security, correctness, reliability, and maintainability, identifying problems that automated tests may miss.

• Enable engineering teams by configuring assistants, skills, hooks, and MCP servers, while sharing effective practices and supporting colleagues.

• Develop React-based interfaces and APIs for internal tools, dashboards, and summaries, ensuring outputs are accessible to agents, command-line interfaces, and Slack.

• Document architecture, workflows, and technical decisions through diagrams, runbooks, and decision records.

Requirements:

• Demonstrated experience shipping production LLM-powered features, including prompt design, tool calling, structured outputs, and long-context workflows, with the ability to explain evaluation strategies, production failures, and corrective actions.

• Strong TypeScript and Node.js skills, including asynchronous programming, production application development, testing, and monorepo tooling.

• Proficiency in Python for evaluation workflows, data analysis, and scripting.

• Hands-on experience with AWS serverless technologies, particularly Lambda, Step Functions, DynamoDB, IAM, event-driven architectures, and Amazon Bedrock.

• Experience safely reviewing and modifying Terraform infrastructure across multiple environments.

• Practical SQL and NoSQL database experience, including schema changes and migrations in live systems.

• Strong observability and debugging skills, including designing metrics, logs, and alerts for non-deterministic AI systems.

• Proficiency in CI/CD practices; experience with GitLab CI/CD is preferred.

• Regular use of AI-assisted development tools, with the ability to validate generated code and assess its quality.

• Fluent spoken and written English, with strong communication skills and the ability to explain technical trade-offs, collaborate across teams, and encourage adoption of effective engineering practices.

The following qualifications are desirable:

• Experience with multi-agent architectures, MCP servers, or LLM evaluation frameworks such as Strands Evals.

• Knowledge of LLM cost optimization techniques, including model routing, prompt caching, and token budgets.

• Understanding of prompt-injection defenses and AI agent security.

• Experience with React and GraphQL for internal applications and developer tools.

• Familiarity with Java and Spring Boot for integrating with existing services.

• Experience with code intelligence, retrieval systems, indexing, symbol search, or knowledge bundles.

• Knowledge of Kubernetes, AWS AppSync, and EventBridge.

• Experience with Playwright or Cucumber for automated testing.

• Anthropic Claude Certified Developer or Architect certification.

Benefits:

• Fully remote work: Work remotely from Brazil with flexibility in your working environment.

• Health and well-being: Company-paid medical insurance, mental health programs, and five additional sick-leave days per year without documentation requirements.

• Paid time off: 20 working days of paid vacation annually, in addition to local bank holidays.

• Professional development: Access internal meetups, conferences, workshops, a Udemy license, language courses, and company-paid certifications.

• Career growth: Learn from a global community of experienced professionals and expand your technical expertise.

• Internal mobility: Access opportunities to change projects when appropriate to support your professional development and career goals.

• Long-term employment: Join a stable, ongoing professional environment with opportunities to grow.

• International projects: Contribute to large-scale engineering initiatives for international and fast-growing clients.

• Collaborative culture: Work in a welcoming environment that encourages knowledge sharing, open communication, teamwork, and regular team-building activities.

• Modern technology: Work with emerging AI technologies and engineering practices to develop solutions with meaningful real-world impact.