2 days ago
Remote, BrazilSenior
Responsibilities
- Build production AI agents with TypeScript services on AWS using Lambda, Step Functions, DynamoDB, Bedrock, Strands or LangGraph, and AI SDKs.
- Design agent behavior, sandboxed runtimes, scoped tool access, worktree-contained reads, and budget and timeout protections.
- Create evaluation systems with golden sets, production replays, calibrated judges, and release gates based on recall, precision, and false-positive rates.
- Develop observability through reason-coded metrics, structured logs, alerts, and production debugging in Splunk and VictoriaMetrics.
- Maintain Terraform infrastructure across environments and improve GitLab CI/CD for build, test, deployment, and quality gates.
- Build resilient integrations that handle retries, rate limits, permanent failures, and stale state.
- Review AI-generated code for security, correctness, and maintainability, and help teams configure assistants, skills, hooks, and MCP servers.
- Build React interfaces and APIs for summaries, dashboards, and internal tooling consumable by agents, CLIs, and Slack.
- Document systems with architecture diagrams, sequence diagrams, runbooks, and decision records.
Requirements
- Strong production TypeScript and Node.js experience, including asynchronous code, testing, and monorepo tooling.
- Proficiency in Python for evaluations, analysis, and scripting.
- Hands-on AWS serverless experience with Lambda, Step Functions, DynamoDB, IAM, event-driven design, and Bedrock.
- Experience safely reading and modifying Terraform across environments.
- Hands-on NoSQL and SQL experience, including live schema changes and migrations.
- Experience designing metrics, logs, and alarms for non-deterministic systems and debugging production issues.
- Proficiency with CI/CD, ideally GitLab CI/CD.
- Production experience shipping LLM API features involving prompts, tool calling, structured output, and long context, with the ability to explain evaluation releases, failures, and fixes.
- Daily use of AI coding assistants and ability to verify their output.
- Fluent spoken and written English with the ability to explain trade-offs and drive team adoption.
- Desirable qualifications include multi-agent systems, MCP servers, evaluation frameworks, LLM cost controls, prompt-injection defense, agent security, React, GraphQL, Java, Spring Boot, code intelligence or retrieval, Kubernetes, AWS AppSync, EventBridge, Playwright, Cucumber, or Claude certification.
Benefits
- Full-time employment with 100% remote work from Brazil.
- Company-paid medical insurance, mental health programs, and five undocumented sick-leave days per year.
- Twenty working days of paid vacation plus local bank holidays.
- Internal events, meetups, conferences, workshops, Udemy access, language courses, and company-paid certifications.
- Internal Mobility Program and opportunities to work with international, fast-growing clients.
- Friendly, collaborative workplace with an open-door policy, informal atmosphere, and regular team-building events.
Tech Stack
Amazon DynamoDBAWSCucumberGitLab CI/CDGraphQLJavaKubernetesNode.jsPythonReactSplunkSpring BootTerraformTypeScript
Categories
About Ciklum
Ciklum is an IT services firm that builds custom digital products and provides nearshore engineering teams, QA, DevOps, data analytics, and UX for enterprises and high-growth startups. It operates a services model spanning product engineering, e-commerce solutions, and managed delivery centers. Founded in 2002 and headquartered in London, the privately held company serves global clients including Just Eat and Zurich Insurance.