About the role
Ciklum is looking for a proactive Senior/Lead Full Stack AI Engineer to join our team in Brazil.
About the role:
As a Senior/Lead Full Stack AI Engineer, you'll become a part of a cross-functional development team engineering experience of tomorrow.
In this role, you will bring a broad technical perspective and adapt across modern stacks, building scalable React/TypeScript interfaces, resilient Python backend services, and integrating production-grade LLM capabilities on AWS. You will be an AI champion within the engineering organization, elevating developer productivity and delivery excellence.
Responsibilities:
Full-Stack Development: Design, implement, and maintain high-performance, robust frontend applications with modern React, TypeScript, and Node.js monorepo tooling
Backend & Automation: Develop scalable backend services, automation scripts, and evaluation pipelines primarily using Python
LLM Production Features: Build, test, and ship production-ready LLM features (prompt engineering, tool/function calling, structured outputs, long-context handling)
Evaluations & Quality Gates: Define and implement robust evaluation (eval) frameworks to gate releases, analyze non-deterministic failure modes, and iterate based on benchmark metrics
Cloud Architecture & Infrastructure: Design, configure, and maintain infrastructure on AWS (leveraging both serverless tools and compute/container components like ECS/EKS, VPC networking, and IAM) safely managed via Terraform (IaC)
Data Management: Work hands-on with both SQL and NoSQL databases, executing schema evolutions and zero-downtime production migrations
Observability & Reliability: Set up granular metrics, structured logs, and alerts for distributed/non-deterministic architectures; lead production incident troubleshooting and root-cause analysis
CI/CD & Delivery: Maintain and enhance automated CI/CD pipelines (preferably GitLab CI/CD) ensuring rapid, reliable deployments
AI Advocacy & Culture: Champion AI-assisted engineering tools (Copilot, Cursor, LLM APIs) and best practices across the team to drive engineering efficiency and knowledge sharing
Technical Alignment: Collaborate closely with team members and stakeholders, articulating architectural trade-offs and driving clarity in technical decisions
Requirements:
Full-stack & Versatility: Broad technical perspective with an emphasis on adaptability across modern software stacks and architectures, favoring breadth and quick ramp-up over narrow specialization
Frontend & TypeScript: Strong production experience with modern React and TypeScript (including Node.js, asynchronous patterns, comprehensive testing, and monorepo tooling)
Backend & Scripting: Working proficiency with Python for backend services, evaluations, data analysis, and automation tooling
AWS Beyond Serverless: Practical hands-on experience across the AWS ecosystem—extending beyond serverless (Lambda, Step Functions, DynamoDB, Bedrock) to broader architectural components such as containers (ECS/EKS), networking, compute, and IAM
LLM Features in Production: Proven track record of shipping features leveraging LLM APIs (prompts, tool calling, structured outputs, long context), with the ability to describe the evals that gated releases, failure modes encountered, and iterations deployed
AI Champion Mindset: Enthusiastic, proactive embrace of AI-assisted engineering tools in daily workflows (e.g., GitHub Copilot, Cursor, LLM APIs), combined with the drive to champion AI-first practices across the team
Infrastructure as Code (IaC): Ability to read, understand, and safely modify Terraform configurations across environments
Data & Persistence: Hands-on experience with both NoSQL and SQL data stores, including schema changes and live-system migrations
Observability: Ability to design metrics, logs, and alarms tailored for non-deterministic systems, effectively debugging production issues from telemetry data
CI/CD: Proficiency with modern CI/CD pipelines, ideally GitLab CI/CD
Communication: Upper-intermediate or fluent written and spoken English, with strong skills in articulating trade-offs and aligning cross-functional teams around technical decisions
Desirable:
Hands-on experience with multi-agent systems, Model Context Protocol (MCP) servers, or specialized LLM evaluation frameworks
Practical understanding of LLM cost control strategies (model routing, prompt caching, token budgets, rate-limiting)
Knowledge of prompt-injection defenses and agentic security patterns
Experience building or consuming internal APIs using GraphQL
Experience in code intelligence or semantic retrieval workflows (indexing, symbol/AST search, knowledge bundles)
Practical exposure to Kubernetes, AWS AppSync, and AWS EventBridge
Automated testing with Playwright or Cucumber
Certifications such as Claude Certified Developer or Claude Certified 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 employment with 20 working-days paid vacation and local bank holidays
Flexibility: 100% remote work mode
Opportunities: we value our specialists and always find the best options for them. Our Internal Mobility Program helps change a project if needed to help you grow, excel professionally and fulfill your potential
Global impact: work on large-scale projects that redefine industries with international and fast-growing clients
Welcoming environment: feel empowered with a friendly team, open-door policy, informal atmosphere within the company and regular team-building events
About us:
At Ciklum, we are always exploring innovations, empowering each other to achieve more, and engineering solutions that matter. With us, you’ll work with cutting-edge technologies, contribute to impactful projects, and be part of a One Team culture that values collaboration and progress.
As we expand into Latin America, every Ciklumer is helping to shape our story. Collaborate with seasoned experts and make a global impact backed by two decades of industry leadership.
Explore, empower, engineer with Ciklum!
Interested already? We would love to get to know you! Submit your application. We can’t wait to see you at Ciklum.
Originally posted on Himalayas
