Platform Software Development
• Lead and develop one or more engineering teams delivering shared capabilities for deploying, running, and governing enterprise AI agents.
• Own team execution across assigned Agent Platform capabilities, including control plane and data plane resources, developer experience, human-in-the-loop workflows, enterprise connectors, and observability.
• Contribute to platform strategy by translating customer needs and operational experience into technical priorities and delivery plans.
• Establish consistent APIs, SDKs, CLI workflows, and resource lifecycle contracts; guide compatibility, deprecation, and migration decisions.
Software Development — Design, Testing, and Optimization
• Guide teams in translating requirements into maintainable services with clear designs, acceptance criteria, and operational documentation.
• Lead technical reviews across platform components, addressing correctness, failure handling, testability, accessibility, and operational readiness.
• Establish testing strategies covering resource provisioning, agent invocation, enterprise connectors, human approval and input flows, and telemetry.
• Direct debugging and performance optimization across control plane services, data plane execution, and dependent systems.
• Improve developer workflows for onboarding, configuration, deployment, troubleshooting, and upgrades.
Software Architecture — System Design
• Guide architecture decisions for control plane resource management and data plane execution, with clear service boundaries and ownership.
• Ensure human-in-the-loop capabilities support reliable approval, input, and execution-resumption flows, including timeouts and failure recovery.
• Guide enterprise connector designs that support consistent authentication, authorization, configuration, and error handling.
• Establish observability patterns that connect resource operations, agent runs, human interactions, and tool calls to support diagnosis and cost analysis.
• Review designs for scalability, tenant isolation, resilience, compatibility, and safe rollout and rollback.
Customer Support and Issue Resolution
• Own engineering prioritization and escalation for issues affecting resource provisioning, agent execution, developer tooling, human-in-the-loop workflows, connectors, and observability within the team’s scope.
• Coordinate investigations with infrastructure, security, dependent service owners, and consuming teams; communicate impact, workarounds, and resolution plans.
• Turn recurring incidents and customer feedback into improvements to platform capabilities, diagnostics, documentation, and self-service workflows.
• Ensure significant incidents produce clear corrective actions with accountable owners and follow-through.
Security and Governance
• Partner with security teams to implement requirements for resource access, agent identity, tenant isolation, secrets management, and enterprise connectivity.
• Ensure agent actions, connector access, and human approval workflows enforce applicable authorization boundaries and preserve auditability.
• Hold teams accountable for secure development, security reviews, vulnerability remediation, and safe handling of customer data throughout the service lifecycle.
Development Operations and Reliability
• Establish SLOs, actionable monitoring, on-call readiness, and operational playbooks for owned services.
• Review error budgets, incident trends, capacity, latency, and resource consumption; balance reliability improvements with feature commitments.
• Lead safe upgrades to platform services, runtime dependencies, and connectors through automated validation, staged deployment, and rollback procedures.
• Improve infrastructure and inference cost efficiency while meeting reliability and performance objectives.
• Build operational ownership into service design, delivery, and ongoing maintenance.
Core Responsibilities
Planning and Execution
• Translate platform priorities into achievable team plans with clear ownership, milestones, dependencies, and success measures.
• Balance feature delivery, reliability, security, performance, cost efficiency, and technical debt within available staffing and budget.
• Adjust plans as customer needs, delivery risks, and dependencies change.
Collaboration and Partnership
• Partner with product, security, infrastructure, and consuming teams to align priorities, resolve dependencies, and make informed tradeoffs.
• Coordinate onboarding, migration, and adoption plans with clear readiness criteria, documentation, and support expectations.
• Encourage diverse perspectives and constructive technical discussion across teams.
Problem Solving
• Guide teams through complex problems spanning control plane state, data plane execution, human interactions, enterprise integrations, and telemetry.
• Use customer impact, operational evidence, and long-term maintainability to prioritize solutions and resolve escalations.
Continuous Learning
• Build team expertise in distributed systems, agent execution, developer tooling, human-in-the-loop patterns, enterprise integration, and observability.
• Evaluate emerging technologies against customer needs, security requirements, operating costs, and service maturity.
Continuous Improvement
• Use delivery, reliability, performance, cost, and adoption data to identify and measure improvements.
• Reduce manual provisioning, onboarding, troubleshooting, and maintenance through automation, clearer interfaces, and reusable capabilities.
Performance and Development
• Hire, coach, and develop engineers; set clear expectations and provide regular, actionable feedback.
• Align individual development goals with team needs and create opportunities for technical leadership and career growth.
• Establish clear ownership, address skill and staffing gaps, and build teams accountable for both delivery and production outcomes.