Senior Full Stack Engineer

Ciklum is looking for a Senior Full Stack Engineer to join our team full-time in Brazil.

We are a custom product engineering company that supports both multinational organizations and scaling startups to solve their most complex business challenges. With a global team of over 4,000 highly skilled developers, consultants, analysts and product owners, we engineer technology that redefines industries and shapes the way people live.

About the role:

As a Senior Full Stack Engineer, become a part of a cross-functional development team engineering experiences of tomorrow.

Responsibilities:

Build production AI agents: develop TypeScript services on AWS (Lambda, Step Functions, DynamoDB, Bedrock) using Strands or LangGraph and AI SDKs

Design agent behavior: define what the model investigates and what code enforces

Sandbox agents: build read-only runtimes, scoped tool access, worktree-contained reads, and budget/timeout guards against model misbehavior

Evaluate AI features: build golden sets and production replays, calibrate judges, gate changes on recall, precision and false-positive rate, and compare models and effort levels before release

Ensure observability: emit reason-coded metrics and structured logs, alert on failures, and investigate production misses in Splunk and VictoriaMetrics

Run infrastructure: maintain Terraform roots across environments under tagging and permission-boundary rules; improve GitLab CI/CD for build, test, deploy and quality gates

Build integrations resilient to retries, rate limits, permanent failures and stale state

Use AI to write/review code; keep agent context current

Review AI-written changes for security, correctness and maintainability, catching issues tests miss

Enable teams: configure assistants, skills, hooks and MCP servers; pair with engineers and share proven practices

Build agent-facing tools: React and APIs for summaries, dashboards and internal tooling, with outputs readable by agents, CLIs and Slack

Document systems with architecture/sequence diagrams, runbooks and decision records

Requirements:

LLM production experience: shipped LLM API features (prompts, tool calling, structured output, long context); can explain release evals, failures and fixes

TypeScript: strong production TypeScript and Node, async code, testing and monorepo tooling

Python: proficiency in evals, analysis and scripting

AWS serverless: Lambda, Step Functions, DynamoDB, IAM, event-driven design and Bedrock

Infrastructure as code: safely read and modify Terraform across environments

Data: hands-on NoSQL/SQL experience, including live schema changes and migrations

Observability: design metrics, logs and alarms for non-deterministic systems and debug issues

CI/CD: proficiency with CI/CD, ideally GitLab CI/CD

AI-assisted development: daily AI coding assistant use; verify its output

Communication: fluent spoken and written English; explain trade-offs and drive team adoption

Desirable:

Multi-agent systems, MCP servers or eval frameworks (e.g. Strands Evals)

LLM cost control: model routing, prompt caching, token budgets

Prompt-injection defense and agent security

React and GraphQL for internal tools

Java and Spring Boot for existing service integration

Code intelligence or retrieval (indexing, symbol search, knowledge bundles)

Kubernetes, AWS AppSync and EventBridge

Playwright/Cucumber test automation

Claude Certified Developer or Architect (Anthropic)

What’s in it for you?

Care: your mental and physical health is our priority. We ensure comprehensive company-paid medical insurance and mental health programs, 5 undocumented sick-leave days per year

Tailored education path: boost your skills and knowledge with our regular internal events (meetups, conferences, workshops), Udemy license, language courses and company-paid certifications

Growth environment: share your experience and level up your expertise with a community of skilled professionals, locally and globally

Long-term empl