2 days ago
Remote, PolandSenior
Responsibilities
- Build production AI agents with TypeScript services on AWS using Lambda, Step Functions, DynamoDB, Bedrock, Strands, LangGraph, and AI SDKs.
- Define agent behavior, implement sandboxed runtimes and scoped tool access, and add budget, timeout, and permission controls.
- Build evaluation systems using golden sets, production replays, calibrated judges, and quality gates based on recall, precision, and false-positive rates.
- Implement observability through reason-coded metrics, structured logs, alerts, Splunk, and VictoriaMetrics, and investigate production failures.
- Maintain Terraform infrastructure across environments and improve GitLab CI/CD for build, test, deployment, and quality gates.
- Build resilient integrations and agent-facing React interfaces, APIs, dashboards, summaries, and internal tools.
- Review AI-generated code for security, correctness, and maintainability; configure assistants, skills, hooks, and MCP servers; and enable engineering teams.
- Document systems with architecture and sequence diagrams, runbooks, and decision records.
Requirements
- Strong production experience with modern React and TypeScript, including Node.js, asynchronous programming, testing, and monorepo tooling.
- Working proficiency with Python for backend services, evaluations, analysis, and automation.
- Hands-on AWS experience beyond serverless, including Lambda, Step Functions, DynamoDB, Bedrock, containers, networking, compute, and IAM.
- Experience shipping production features using LLM APIs, including prompts, tool calling, structured output, and long context, with the ability to explain release evaluations and failures.
- Ability to read and safely modify Terraform configurations across environments.
- Hands-on experience with both NoSQL and SQL data stores, schema changes, and live-system migrations.
- Ability to design metrics, logs, and alarms for non-deterministic systems and debug production issues using observability data.
- Proficiency with modern CI/CD pipelines, preferably GitLab CI/CD.
- Fluent written and spoken English with the ability to communicate trade-offs and align teams around technical decisions.
- Desirable experience with multi-agent systems, MCP servers, evaluation frameworks, LLM cost controls, prompt-injection defense, agent security, GraphQL, code intelligence or retrieval, Kubernetes, AWS AppSync, EventBridge, Playwright, Cucumber, or Claude certifications.
Benefits
- Full remote working possibilities in Poland.
- Internal meetups, conferences, workshops, Udemy access, language courses, and company-paid certifications.
- Internal mobility opportunities across diverse domains and projects.
- Company-paid premium medical package through Luxmed.
- MyBenefit cafeteria platform with flexible lifestyle perks.
- Collaborative community and opportunities to work on large-scale projects with global impact.
Tech Stack
Amazon DynamoDBAWSCucumberGitLab CI/CDGraphQLJavaKubernetesNode.jsPythonReactSplunkSpring BootSQLTerraformTypeScript
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.