Deliver AI-enabled automation solutions end-to-end — from agent/automation build through integration and into production operation — against designs set by the Architect. Bridge the gap between architecture and delivery, owning hands-on build, deployment, and day-to-day production support of automation and AI components.
Roles and Responsibilities
- Build and deploy AI agents and LLM-based automations against architecture designs
- Develop integrations between automation/agent layers and enterprise systems via APIs, webhooks, and event-driven patterns
- Own the full delivery lifecycle for assigned components: development, testing, deployment, and production support
- Implement and maintain deployment pipelines (CI/CD) for AI services and automations on cloud platforms
- Set up and maintain monitoring/observability for deployed agents and automations, catching failures, drift, or performance degradation in production
- Troubleshoot and resolve production issues across the automation/AI/integration stack, escalating to the Architect where design changes are needed
- Collaborate closely with the Architect on design feasibility and technical constraints during solutioning
- Collaborate with the Integration Architect on data/API dependencies feeding automations and agents
- Document technical builds, configurations, and runbooks to support handover and ongoing operations
- Contribute reusable components, templates, and patterns for future engagements
- Support testing and validation of automation/agent outputs prior to production release
- Participate in code/design reviews led by the Architect
Required Skills/Experience
- Hands-on development experience building automations or agents; RPA background helpful but must extend into AI/LLM-based build work
- Practical experience with LLM APIs, agent frameworks, and integrating them into working production systems, not just conceptual familiarity
- Strong API/integration development skills, including REST, webhooks, and event streaming
- Hands-on cloud platform experience across Azure/AWS/GCP, including deployment and basic infrastructure-as-code
- Experience running production monitoring/observability for deployed services, including logging, alerting, and dashboards
- Comfortable working across the stack rather than in a single specialism — automation, integration, and AI, not just one
- Debugging and troubleshooting skills across distributed, cloud-hosted systems
- Familiarity with version control, CI/CD pipelines, and standard software engineering practices
- Ability to work from architectural designs and translate them into working, production-ready builds