Staff Software Engineer - Agent Observability (Galileo)

Job Description

Lead the architecture, design, and delivery of scalable backend systems and customer-facing capabilities for AI agent observability, tracing, evaluation, metrics, and control. Write production code, guide technical initiatives and reviews, mentor engineers, collaborate across Cisco and Splunk, and support production reliability through an on-call rotation.

Requirements: Requires a bachelor's degree with at least 8 years of related experience, a master's degree with at least 6 years, or equivalent practical experience, plus 8 or more years developing production backend services in Python and/or Go. Candidates must have experience leading multi-engineer technical delivery and designing scalable, high-throughput distributed systems, backend architectures, and APIs; AI/ML, observability, streaming data, and cross-team leadership experience are preferred.

Key Skills: Python, Go, Backend Software Development, Distributed Systems, API Design, System Architecture, AI Observability, Distributed Tracing, Multimodal Evaluation, Generative AI, Large Language Models, Agentic Applications, Telemetry Processing, Kafka, ClickHouse, OpenTelemetry

Benefits: Medical Insurance, Dental Insurance, Vision Insurance, 401(k) With Matching Contribution, Paid Parental Leave, Short-Term Disability Coverage, Long-Term Disability Coverage, Basic Life Insurance, Restricted Stock Units, Paid Holidays, Floating Holiday, Birthday Day Off, Year-End Holiday Shutdown, Personal Wellness Days, Paid Vacation, Flexible Vacation Time, Sick Leave, Family Emergency Leave, Paid Volunteer Days, Annual Bonuses