Principal CX Architect

Caylent

5d•CA$180,000 - CA$202,000•Remote

About The Position

Caylent is an AI-first cloud services company that helps organizations turn ambitious ideas into meaningful business impact. As an AWS Premier Tier Services Partner and a charter member of Anthropic’s Claude Partner Network, we combine deep expertise in AWS, artificial intelligence, and Anthropic’s Claude platform to help customers modernize their technology, build intelligent products, and move AI from experimentation into production. Our capabilities span generative and agentic AI, cloud migration and modernization, cloud-native application development, data and analytics, DevOps, managed services, security and compliance, and customer experience transformation. At Caylent, our people always come first. We are a fully remote global company with employees in Canada, the United States and Latin America. We celebrate the culture of each of our team members and foster a community of technological curiosity. Come talk to us to learn more about what it means to be a Caylien! The Mission We are seeking a talented Principal Architect to join our growing CXE (Contact Center Experience) practice. The right candidate is someone who combines deep hands-on Amazon Connect and conversational AI expertise with the technical leadership to own delivery of complex, AI-native contact center solutions end to end. Your mission will be to lead the architecture and technical delivery of Amazon Connect and AI agent solutions for our customers, providing expert guidance, managing technical risk, and ensuring that scope, deliverables, and objectives align to business outcomes and Caylent best practices while leading the Caylent technical team to deliver with excellence.

Requirements

10+ years of hands-on software engineering experience, including 2+ years building on Amazon Connect or comparable CCaaS platforms at enterprise scale
Strong, current Amazon Connect skills: contact flows, routing, Cases and Tasks, Contact Lens, Customer Profiles, Streams API, and the Connect data/analytics stack
Hands-on experience with conversational and generative AI, Amazon Lex plus LLM-based development (Amazon Bedrock, Q in Connect, or equivalent), including prompt engineering and tool calling
Strong Python, Typescript/Node.js, Javascript, and React experience; solid AWS serverless engineering (Lambda, EventBridge, API Gateway, DynamoDB, Step Functions)
Experience with docker containers, web applications, databases (i.e. DynamoDB, SQL, Aurora)
Infrastructure as code proficiency with AWS CDK or Terraform, including multi-account deployment patterns
Understanding of RAG concepts and LLMOps
Experience shipping and supporting production systems, testing discipline, observability instrumentation, and incident debugging across the full stack
Clear communication with customer-facing composure, able to demo your work, explain trade-offs, and run working sessions with both client engineers and C-suite members

Nice To Haves

AWS certifications (Solutions Architect, Developer, or ML/Connect-relevant Specialty)
Contact center migration experience (i.e. Avaya, Genesys, Connect, NICE)
Contact center operations fluency: Quality management, outbound compliance, and CX KPIs (containment, AHT, CSAT, NPS, SLA)
Consulting or client-delivery background

Responsibilities

Build AI-native self-service using Amazon Connect AI agents, Amazon Q in Connect, and Amazon Bedrock (Claude model family), implementing multi-agent orchestration patterns, with orchestrator agents delegating to task-specific agents and escalation paths to human queues
Engineer prompts and tool-calling integrations at production scale: SearchProfiles lookups, case creation, external API tools, authentication flows, and guardrails against hallucination and verification loops
Implement barge-in handling, fallback, and error-recovery behavior for voice AI, and validate it with turn-by-turn trace analysis
Optimize inference cost and latency hands-on: model tier selection (Haiku vs. Sonnet vs. Opus), prompt caching, and token budgeting against containment-rate targets
Diagnose AI agent performance using observability tooling (agent spans and CloudWatch) that correlates contact flow logs, conversation transcripts, AI agent spans, tool executions, and token usage to isolate latency, cost, and quality issues
Build conversational experiences where intent-based NLU is the right fit, including multilingual support and SSML-tuned voice interactions
Leverage Claude Code to enhance, develop, and/or create system architectures and components
Build contact flows that integrate AI agents, Lambda-backed business logic, Customer Profiles, and dynamic data-driven routing
Implement Amazon Connect Cases and Tasks solutions: case templates, queue-based work allocation, SLA monitoring, approval workflows, and migrations from legacy case systems
Configure and operationalize Contact Lens for real-time sentiment, post-contact summaries, category rules, and quality management
Implement proficiency-based and attribute-driven routing, outbound campaigns (including answering machine detection and compliance controls)
Build out the Amazon Connect analytics data lake (Glue, Lake Formation, Athena) and QuickSight dashboards for real-time operations and executive reporting
Support legacy platform migrations (i.e. Avaya, Genesys, Connect, NICE): flow conversion, data migration, parallel-run validation, and production cutover on live contact centers
Build custom Agent Workspace experiences with the Amazon Connect Streams API, third-party app embedding, and CRM screen-pop integrations
Build serverless, event-driven backends with Lambda, EventBridge, Step Functions, SQS/SNS, DynamoDB, and Kinesis for real-time event processing and customer journey orchestration
Author infrastructure as code with AWS CDK (TypeScript) as the primary tool, CloudFormation, or Terraform where customer environments require them
Build and maintain CI/CD pipelines (GitHub Actions) and automated test suites: Jest/Vitest/PyTest, Playwright E2E and API tests, and integration tests against live Connect instances
Follow phased rollout patterns for production contact centers where downtime is measured in missed calls; write deployment runbooks
Instrument monitoring and alerting (CloudWatch metrics, alarms, and custom dashboards across voice, chat, tasks, queues, agents, Lambda, and AI agents) and participate in production incident triage
Apply security and compliance baselines in everything you ship: least-privilege IAM, DevSecOps scanning, encryption standards
Work directly with customer engineering teams: pair on integrations, run technical working sessions, demo completed workstreams, and lead knowledge transfer so customers can operate what you build
Own architecture decisions within your workstream; evaluate native Connect capability before custom builds ("configuration over customization"), surface trade-offs to practice leads, and document decisions
Perform code reviews, uphold engineering standards, and mentor junior and mid-level CX engineers through pairing and review feedback
Contribute reusable assets back to the practice: shared CDK constructs, skills/plugins, demo environments, and internal tooling, so the next engagement starts further ahead
Support pre-sales when needed: build proof-of-concept demos and provide implementation-grounded input on estimates and SOW technical scope
Lead a 5–10 person team of BAs, engineers, and architects to deliver the solution, providing day-to-day technical direction and unblocking the team
Own solution delivery planning, ensuring scope, deliverables, and objectives stay aligned to business goals and Caylent best practices
Drive risk management and mitigation, identifying technical risks early and steering the team through resolution
Serve as the primary technical escalation point for the client, translating business needs into technical direction for the team
Ensure technical delivery quality, reviewing architecture and implementation decisions against Caylent standards
Mentor and guide team members, fostering growth and consistent technical practices across the group