Production Support Engineer

About the Role

Ampliwork builds Enterprise-Grade AI Agents that amplify Human Potential™ to drive business productivity and growth since 2017. Ampliwork’s AI Agents streamline complex multi-step workflows in highly regulated industries such as Financial Services. This is a new role focused on being the first line of response for client users of our AI platforms. You will handle everything that arrives from client users, resolve what can be resolved, investigate what needs investigating, and escalate only the items that genuinely require an engineer. The role covers several client deployments, requiring you to manage multiple contexts and prioritize effectively across them.

Responsibilities

• First response and first-line resolution: Own the support queue end-to-end: acknowledge new requests promptly, classify them by severity, and drive every item to resolution or complete handoff. Answer usage and configuration questions directly from documentation and your understanding of the product. Resolve non-defect issues such as questions, workflow misunderstandings, and enhancement ideas.
• Technical investigation and triage: Carry out first-level technical triage: inspect application and cloud logs, run read-only database queries, reproduce reported behavior, and form your own view of the likely cause. Read application code to locate relevant logic and confirm or rule out hypotheses. Use internal AI triage tooling as a starting point, correcting its output where necessary.
• Escalation and follow-through: Escalate only the tickets that need it, with a reproducible case, logs, affected records, and your analysis attached. Create and own tasks sent downstream to engineering, following them through fix, review, and release. Push back on out-of-scope requests and route them appropriately.
• Client communication: Act as the named point of contact for client users via email, support portal, and chat. Keep clients informed with regular status updates, especially for high-severity issues. Maintain clear, courteous communication, even when addressing out-of-scope requests or incorrect severity labels.
• Knowledge, reporting, and improvement: Contribute to the knowledge base with known issues, workarounds, runbooks, and standard responses. Produce weekly support reports for each account, covering volume, mix, response performance, and recurring issues. Provide feedback on triage tooling to improve its accuracy.

Requirements

• Three to five years in application support, production support, technical support engineering, or a comparable client-facing technical role.
• Python: Able to read and debug application code, and write small scripts to inspect data or verify behavior.
• Cloud platforms (AWS or equivalent): Comfortable navigating logs and monitoring to trace issues through a running system.
• SQL and PostgreSQL: Able to write queries to answer data-level questions independently.
• A track record of resolving tickets rather than routing them. At interview, you will discuss issues you closed that others might have escalated.
• Excellent written English. Most of your output is writing, often directly to clients. Strong verbal communication skills are also important for client calls.
• Self-starting and methodical: take notes, follow up on open items, and keep track of outstanding tasks without prompting.
• Comfortable being assertive: challenge severity labels, decline out-of-scope requests, and communicate non-defect behaviors to clients.
• Able to manage multiple accounts and products simultaneously without losing track.
• Able to learn complex domain applications quickly, understanding business logic rather than just recognizing screens.
• Accountable for response times and client relationships, not just ticket counts.

Desirable Skills

• Experience working to defined service levels in enterprise, regulated, or audited environments.
• Experience with enterprise ticketing platforms and downstream engineering task trackers.
• Additional languages.
• Exposure to financial services, professional services, insurance, tax, or transport operations.
• Experience working alongside AI agents or automation within a support workflow.

How Success Is Measured

• First 30 days: Own the queue for your first account, acknowledge requests within agreed windows, and classify severity correctly. Actively chase requests waiting on missing information.
• 60 days: Only tickets requiring engineering reach engineering, and they arrive complete and reproducible. Weekly support reports are running, and the knowledge base covers recurring issues.
• 90 days: The same model is running on a second account. Propose product changes to eliminate whole categories of tickets. Own the support process, including intake, routing, escalation, and client reporting.

The headline measure is the proportion of inbound tickets resolved without engineering involvement.

Tooling

• Enterprise ticketing and task tracking
• Microsoft 365
• AWS (logs, monitoring, and managed databases)
• PostgreSQL
• Python
• Git
• Internal AI triage tooling