Senior Technical Program Manager, Services Tools & Diagnostics

Twilio•,

23d•$188,240 - $276,700•Remote

About The Position

Join the GCS Strategy & Operations team as a Senior Technical Program Manager, Service Delivery Systems. This role is responsible for the technical foundation that supports GCS in delivering customer outcomes at scale. This includes intelligent automation, knowledge systems, and decision logic within the service delivery workflows for Technical Account Management, Professional Services, and Engagement Management teams. The role involves designing and building systems, including AI workflows, under the Customer Experience Operations (CXO) governance model, with accountability for GCS business outcomes such as resolution rates and revenue-per-headcount. This position blends engineering and program management, requiring weekly coding while focusing on GCS customer outcomes rather than a technology roadmap. Collaboration with GCS Program Managers, Technical Account Management, Professional Services, and Twilio Engineering teams is essential to translate business requirements into reliable systems.

Requirements

7+ years of experience building production software or technical systems in roles such as platform engineering, solutions architecture, or hands-on technical program management.
Production-quality proficiency in Python and/or TypeScript (Node.js).
Fluency in REST API integration fundamentals: authentication (OAuth 2.0, API keys, token refresh), webhooks, pagination, rate limiting, error handling and retries, and JSON transformation.
Hands-on experience building AI systems with large language models, including tool use/function calling, structured outputs, prompt architecture, and evaluation harnesses.
Experience building and deploying MCP servers to connect enterprise systems.
Deep understanding of how large language models work, including their reasoning, failure points, and underlying causes.
Fluency in RAG architectures, prompt engineering patterns, and agent frameworks.
Advanced SQL, including analytical queries against columnar stores like ClickHouse.
Dashboard and application development experience across Grafana, Salesforce, Tableau, Looker, and Airtable.
Strong engineering practices: Git-based version control, code review, basic CI, and least-privilege patterns for customer data.
Demonstrated ability to translate business requirements into system specifications.
Ability to explain complex technical behavior to non-technical stakeholders.

Nice To Haves

Experience embedded in a support or professional services organization, building systems for the teams doing the work.
Experience with Zendesk or similar service platforms, including APIs, triggers, and routing logic.
Experience defining metrics and observability for AI systems in production.
Experience running structured A/B tests or evaluations.
Familiarity with Twilio's products or the CPaaS/SaaS domain.

Responsibilities

Architect and build systems that define GCS operations, including account health observability, intelligent routing, knowledge retrieval, and workflow automation across TAM, PS, and EM functions, with a focus on cost optimization.
Build AI workflows using Anthropic Claude API, Claude Agent SDK, and Claude Code, including MCP servers to connect agents with Slack, Jira, Zendesk, Grafana, Airtable, and internal Twilio systems.
Collaborate with CXO to design decision frameworks for system autonomy, human-in-the-loop processes, and guardrails to minimize failure rates, prevent prompt injection, and block unintended behaviors.
Enhance GCS's observability and analytics foundation with production-quality dashboards and integrations across Grafana, Salesforce, Tableau, Looker, and Airtable, selecting the appropriate tool for the audience and data source.
Operate within and help mature CXO's vetting-and-graduation governance model, including versioning, evaluation frameworks, A/B testing, and systematic performance measurement.
Instrument all built systems to track retrieval accuracy, action success rates, deflection, and failure patterns, linking technical performance to GCS outcomes like time to value, resolution rate, cost-per-ticket, and time-to-resolution.
Translate complex system behavior into clear language for director and executive audiences, and produce clear technical documentation for dependent teams.