Technical Systems Engineer

This is a hybrid role that requires you to be in the office three days per week at either Cisco’s San Jose, CA or RTP, NC location, depending on your location.

The Commerce Quote to Order team enables Cisco’s go-to-market strategy with an exceptional commercial platform, focusing on hardware, software subscription, and services through data-driven solutions. At Cisco Commerce, our software engineers develop the next-generation CPQ (Configure Price and Quote) Software solutions that manage $60+ billions of Cisco revenue. We handle substantial data with multiple flows, requiring versatile and enthusiastic engineers to solve the latest challenges and push technology forward. Our teams continuously iterate, solve problems, and collaborate to empower our customers and partners.

As a Technical Systems Engineer with Commerce Product Management & Engineering (part of Cisco IT), You will be at the forefront of sustaining, monitoring, and troubleshooting critical enterprise AI capabilities,including generative AI assistants, conversational agents, and foundational LLM platform infrastructure.

You will be a bridge between the core AI, platform engineering teams, and end-users by diagnosing complex operational issues across Retrieval-Augmented Generation (RAG) pipelines, vector search indexing, model inference endpoints, prompt orchestration layers, and custom Python integrations.

You will collaborate on multi-functional projects to identify areas for improvement. You will analyze internal processes, data, and problems, and identify benefits from new capabilities using emerging digital and cloud technologies.

Responsibilities:

• Act as the main point of contact for production support, managing and resolving tickets across various business units
• Serve as the primary technical escalation point for production issues impacting AI Assistants, conversational interfaces, and foundational AI capabilities.
• Triage, debug, and resolve incidents related to model latency, context overflow, prompt drift, and upstream API failures.
• Monitor agent workflows, multi-tool function calling, and orchestration layers to maintain high availability and adherence to strict operational SLAs.
• Debug and maintain Python-based AI frameworks, microservices, MCPs, and REST API endpoints.
• Develop custom automation scripts, health-check utilities, and synthetic monitoring tests in Python to proactively identify failure modes.
• Monitor AI telemetry, token consumption, error rates, and latency metrics using observability platforms (e.g., Langfuse, LangSmith, Datadog, Splunk).
• Ensure timely and effective resolution of issues while maintaining a high level of customer satisfaction
• Document processes, resolutions, and recurring issues for knowledge management and training purposes.

Minimum Qualifications

• Bachelor’s degree in Engineering with 6–7 years of relevant professional experience.
• 3+ years of experience using or supporting one or more of the following technologies: Java, SQL, PL/SQL, Oracle, MongoDB, Snowflake, AngularJS, Python, APIs (HTTP/RESTful web services), Elastic, or Kibana.
• 3+ years in Technical Support, SRE, Software Engineering, with at least 1–2 years dedicated to supporting AI/ML or LLM-driven applications.

Benefits

• Medical, dental and vision insurance
• 401(k) plan with a Cisco matching contribution
• Paid parental leave
• Short and long-term disability coverage
• Basic life insurance
• 10 paid holidays per full calendar year, plus 1 floating holiday for non-exempt employees
• 1 paid day off for employee’s birthday, paid year-end holiday shutdown, and 4 paid days off for personal wellness
• Non-exempt employees receive 16 days of paid vacation time per full calendar year
• Exempt employees participate in Cisco’s flexible vacation time off program
• 80 hours of sick time off provided on hire date and each January 1st thereafter
• Optional 10 paid days per full calendar year to volunteer