Tier 2 Application Support Specialist

Full-time | Remote | Philippines-based

About the role

Bayanihan Partners is recruiting a Tier 2 Application Support Specialist to support Ultimarii Studio, a cloud-hosted SaaS platform that uses retrieval-augmented generation (RAG), agentic workflows, large language models (LLMs), and customer knowledge sources to produce research-driven drafting and analysis outputs.

You will diagnose application, data, retrieval, integration, and user-impacting issues; apply approved basic fixes; and escalate complex defects to senior developers with clear technical evidence. The role combines customer-facing support, log analysis, API troubleshooting, cloud monitoring, and structured incident communication.

What you will do

• Investigate and resolve Tier 2 issues across the web/mobile interface, orchestration services, retrieval pipeline, vector store, LLM interactions, and external integrations.

• Reproduce reported issues, assess scope and severity, and distinguish user or configuration issues from data ingestion problems, retrieval failures, model/output issues, integration failures, and application defects.

• Diagnose production issues using tools such as Azure Monitor, SIEM dashboards, OpenTelemetry traces, Langfuse, and Prometheus/Grafana.

• Review logs, traces, audit trails, chunk IDs, latency data, API responses, and user/session context to identify likely root causes.

• Apply approved fixes, including configuration and access corrections, data reprocessing requests, workflow reruns, cache/index refreshes, integration credential checks, and runbook-based remediation.

• Triage incidents, prioritize issues, provide timely updates, and assess customer impact.

• Escalate complex bugs, infrastructure issues, security concerns, or product defects with reproduction steps, evidence, suspected cause, affected components, and business impact.

• Communicate clearly with customers, internal stakeholders, and engineering teams.

• Validate fixes, smoke-test affected workflows, and monitor behavior after releases.

• Maintain troubleshooting playbooks, known-error records, escalation templates, and support documentation.

• Identify recurring issues and recommend improvements to monitoring, diagnostics, documentation, product behavior, or support tooling.

What you will bring

• 3+ years of experience in Tier 2 application support, technical support engineering, SaaS operations, or application support analyst roles.

• Strong troubleshooting skills: isolate symptoms, reproduce issues, test hypotheses, and document findings clearly.

• Experience diagnosing cloud-hosted SaaS applications, preferably on Microsoft Azure.

• Working knowledge of APIs, HTTP status codes, JSON payloads, authentication flows, and browser/network debugging.

• Familiarity with logs, metrics, distributed tracing, alerting systems, and incident-management tools.

• Ability to understand modern web and backend systems, including React/TypeScript frontends and Python/FastAPI-style services.

• Comfort working with data pipelines, search/retrieval behaviour, embeddings, vector databases, or AI/LLM-powered applications.

• Strong written communication for customer updates, incident notes, and developer escalations.

• Ability to perform low-risk operational fixes using approved procedures and escalate when code or architecture changes are needed.

Nice to have

• Experience with Azure Kubernetes Service, Azure Container Registry, GitHub Actions, blue/green deployments, or containerized applications.

• Familiarity with RAG systems, LangChain/LangGraph, Milvus or other vector stores, Azure AI Foundry, or LLM observability tools.

• Experience supporting regulated or compliance-sensitive environments, including SOC 2, GDPR, PIPEDA, or Canadian data residency requirements.

• Familiarity with Jira, GitHub Issues, SIEM tools, or similar customer support platforms.

• Basic Python, PowerShell, or TypeScript scripting for diagnostics or support automation.

What success looks like

Accurate, evidence-based triage; safe fixes within approved boundaries; clear, reproducible escalations; timely professional communication; and support knowledge that improves through better runbooks and recurring-issue analysis.