Senior Technical Support Specialist
Posted Updated
Description
- Ema is building the world’s first Universal AI Employee — a production-grade agentic AI platform that automates real enterprise workflows across HR, IT, Finance, and Operations
- Ema’s customers do not run demos. They replace mission-critical, manual business processes with agentic AI systems that operate across multiple SaaS tools, APIs, and human-in-the-loop workflows
- In this world, support is not reactive. Support is production reliability, trust preservation, and system learning. At Ema, Senior Technical Support Specialists are operators of live AI systems, not ticket handlers
- The Senior Support Engineer owns the health, reliability, and trustworthiness of Ema’s deployed agentic AI systems in production. This role sits at the intersection of:
- AI behavior
- Workflow orchestration
- Enterprise integrations
- Customer trust
- Engineering feedback loops
- This is: ❌ Not L1 / call-center support, ❌ Not a “just escalate to engineering” role, ❌ Not reactive firefighting only
- This is: A senior technical escalation role, A production debugging and RCA role, A partner to Engineering, Product, and Implementation, A role with real authority during incidents
- You are the last line of defense between a production issue and customer trust erosion
- You prevent small failures from turning into account-level crises
- You ensure learnings from incidents improve the product and delivery systemically
- Customers trust Ema because issues are handled competently and transparently
- AI failures are explained, mitigated, and prevented — not hand-waved
- Production stability improves over time, not degrades
- You gain rare experience operating agentic AI systems in production
- You build deep expertise across AI, integrations, and workflows
- You can grow into Reliability Engineering, Implementation Leadership, or Product-facing roles
- Diagnosing failures in multi-agent AI workflows
- Deeply understanding Ema’s platform and providing workarounds/alternate approaches to customers facing issues
- Debugging issues spanning:
- AI behavior (false positives / negatives)
- Workflow logic
- Integrations (HRIS, ITSM, IAM, Finance)
- Data quality
- Platform configuration
- Handling Sev-1 / Sev-2 customer specific incidents calmly under customer pressure
- Help Engineering & Product teams Prevent repeated incidents through disciplined RCA
- Converting noisy customer complaints into high-signal engineering feedback
- Own customer-reported issues from intake to resolution adhering strictly to SLAs
- Take responsibility for diagnosis, coordination, and closure; Importantly, provide workarounds to customers to unblock them while engineering fix is made
- Ensure no issue is “lost” between teams
- Act as technical owner even when multiple teams are involved
- Debug agentic workflows end-to-end
- Trace failures across agents, tools, integrations, and humans-in-the-loop
- Identify whether issues are caused by:
- Model behavior
- Prompt / policy logic
- Integration constraints
- Customer configuration
- Provide clear, actionable root cause summaries
- Resolve Sev 1 / Sev 2 Client issues; Escalate to the right team to help solve and close the issue. Keep customer communication calm, factual, and confidence-building
- Communicate during incidents without speculation or panic
- Explain AI failures in a way customers can understand
- Set realistic recovery timelines
- Rebuild trust post-incident through transparency and follow-through
- Write high-signal bug reports and incident summaries
- Advocate for fixes based on customer impact, not noise
- Help Product understand real production behavior
- Ensure support insights influence roadmap and quality improvement
- Improve runbooks, playbooks, and diagnostics
- Improve on-call hygiene and escalation clarity
- Mentor junior support engineers
- Raise the overall support bar at Ema
- Excellent debugging instincts
- Comfortable operating in ambiguous systems
- Able to isolate root cause across layers
- Calm during incidents
- Issues do not bounce — they get owned
- Bias toward permanent fixes
- Communicates clearly with both engineers and customers
- Knows when to escalate and when not to
- Can say “we don’t know yet” credibly
- Respects both customer urgency and engineering quality
- Low ego, high accountability
- Truth-seeking over blame
- Experience supporting enterprise SaaS platforms in production
- APIs and integrations
- Logs, traces, and diagnostics
- 6–9+ years in senior technical support, reliability, or production engineering roles
- Distributed systems
- Customer-facing experience with senior stakeholders
- Experience handling escalations and incidents
- Strong understanding of:
- Familiarity with AWS / GCP / Azure
- Experience with workflow orchestration or agentic systems
- Support or reliability roles in AI / automation platforms
- Background in high-availability, 24×7 systems