Customer Tech Care Lead Customer Care Department - Remote
Stellar Tech
WorldwideremotePosted 1 month ago
Skill Required
Technical-Support-LeadCustomer-Care-LeadsAutomation-EngineerSupport-EngineerTechnical-LeadCustomer-Tech-Care-LeadRemote-Customer-Support-Team-LeadRemote-Customer-Service-ManagerCustomer-Support-Team-LeadRemote-Customer-Support-LeadershipContact-Center-Technology-LeadCustomer-Support-Leaddata engineeringCD pipelinesEngineeringautomationObservabilitydesigningbuildingEmbedded CPythondesignISO 27001OpenAPICI/CDUnityRAGSQLandGenerative AICICDAIContract
Key highlights
- Salary/compensation: Not specified.
- Required experience: 5+ years in automation/technical support/platform engineering with 1–2 years in a lead capacity.
- Key benefit: 21 days annual leave + 10 bank holidays, global remote, company-provided medical expense compensation, AI subscriptions and tools.
- Notable requirement: Hands-on experience building LLM-based agents or AI-driven automation (OpenAI API, function calling, embeddings, or equivalent).
- Key responsibility: Architect and approve every automation solution shipped by the unit; serve as the primary technical intake for all escalated issues.
- This is not a traditional support lead role — majority of time is spent in systems querying databases, reproducing bugs, reading logs, designing automation flows, and evaluating LLM agents.
Role overview
StellarTech is building a Customer Tech Care unit—a specialised engineering squad embedded within Customer Care—whose sole purpose is to technically resolve every user issue that cannot be solved by a standard support agent. As the Lead, you will be the technical authority and organisational backbone: triaging escalated tickets, directing your team of automation engineers, coordinating with product and infrastructure engineering, and personally architecting or approving every solution shipped.
Responsibilities
- Own day-to-day operation: capacity planning, sprint structure, task distribution, and quality standards.
- Mentor and grow automation engineers; define code and architecture review processes.
- Establish and track unit KPIs: ticket deflection rate, automation coverage ratio, recurrence prevention.
- Report unit performance to management; propose headcount and tooling investments backed by data.
- Serve as the primary technical intake point for all escalated issues: reproduce problems, isolate root causes, scope resolution paths.
- Access production/staging systems, internal dashboards, and databases (SQL/NoSQL) to investigate issues directly.
- Analyse logs, event streams, payment records, subscription states, and user journey data.
- Own the diagnostic protocol and ensure team members follow structured investigation runbooks.
- Design and oversee automation solutions that resolve recurring issue categories without human intervention.
- Architect multi-step pipelines spanning Zendesk triggers, internal API calls, and database state changes.
- Define the solution taxonomy (macro vs. API vs. LLM agent vs. DB script) and enforce it across the team.
- Approve all automation flows before production deployment; enforce rollback and monitoring standards.
- Lead design and deployment of LLM-based agents capable of diagnosing and resolving issues autonomously.
- Define agent architecture for context injection: user profile, subscription state, events, ticket history from DB.
- Oversee training loop quality: curate high-quality resolved tickets to improve agent accuracy.
- Evaluate agent performance quantitatively; own escalation decisions vs. further automation.
- Act as authoritative translator between support teams (who observe symptoms) and engineering teams (who own systems).
- Maintain a shared escalation taxonomy and SLA matrix agreed with both Support Director and Engineering leads.
- Own the feedback loop: unit diagnostic output becomes the engineering bug report that ships a fix.
- Coordinate with Product, Backend Engineering, and Data teams to secure required system access and API endpoints.
- Maintain a live runbook library: automation flows, escalation paths, investigation procedures.
- Ensure every automation has a documented failure mode and rollback path.
- Create onboarding materials for new automation engineers.
Requirements
- 5+ years in automation engineering, technical support engineering, or platform engineering.
- 1–2 years in a team lead or tech lead capacity.
- Demonstrated ability to investigate production issues via direct system access: logs, SQL/NoSQL databases, API responses, event streams.
- Hands-on experience building LLM-based agents or AI-driven automation (OpenAI API, function calling, embeddings, or equivalent).
- Strong Python skills; production-quality scripts for automation, data remediation, and API orchestration.
- Experience designing Zendesk automation pipelines (triggers, automations, ZAF apps) or equivalent support platforms.
- Event-driven architecture and API integration patterns (REST, webhooks, async queues).
- Track record owning support metrics: deflection rate, FCR, CSAT, time-to-resolution.
Nice to have
- Low-code/no-code orchestration tools (n8n, Zapier, Make, Rivet) in hybrid architectures.
- B2C or subscription-based product background with high user volume and complex billing/access state.
- CI/CD pipelines and production-level monitoring for automation systems.
- Data engineering concepts: pipeline design, idempotency, retry logic, dead-letter queues.
- RAG architectures, vector databases, or knowledge-base-augmented LLM agents.
- Experience in a regulated environment (GDPR, PCI-DSS, SOC 2).
Benefits
- Innovative environment focused on pushing the envelope in EdTech.
- Global remote work.
- Company-provided medical expense compensation.
- AI subscription and other tools provided.
- Flexible paid time off: 21 days of annual leave + 10 bank holidays.
- Collaborative culture working alongside passionate, driven professionals.
Additional details
- Interview stages: HR Screen/Introduction, Technical Interview, Technical Assignment, Final Interview.
- Originally posted on Himalayas.