Tech Lead Manager (Agentic Runtime)

Glean · Remote — Mountain View, CA, United States

Welcome to the Jungle Posted May 16, 2026 First seen May 18, 2026

Join Glean as a Tech Lead Manager for the Agentic Runtime team. In this role, you will design and operate core runtime services for multi-turn orchestration, tool calling, model routing, memory, streaming, and safety. You will work across distributed systems, production observability, and ML infra integrations to deliver an instant, accurate, and trustworthy experience while optimizing cost and reliability. You will own impactful runtime problems end-to-end, build and evolve core services, and collaborate closely with product, quality, and application teams.

About the role

- Product‑minded: you prioritize customer impact, clear SLAs/SLOs, and pragmatic iteration - Background in one or more areas is a plus: policy/guardrails, multi‑tenant isolation, rate‑limiting, concurrency control, cost optimization - Experience operating services on Kubernetes and at least one major cloud (e.g., GCP, AWS, or Azure) - Practical understanding of LLM/agents building blocks: tool/function calling, structured outputs, streaming, and model selection/routing - Familiarity with event/streaming systems (e.g., Pub/Sub, Kafka), caching (e.g., Redis), and data stores for low‑latency paths - Strong observability and debugging skills: tracing (e.g., OpenTelemetry), metrics, dashboards, and production forensics - BS/BA in Computer Science or related field, or equivalent practical experience - Ownership‑driven with a positive, proactive attitude; comfortable leading projects or learning from battle‑tested engineers - 8+ years of software engineering experience building production distributed systems or cloud‑native applications - 1+ years of engineering management experience - Strong coding skills in at least one of: Python, Go, Java, or C++, with a focus on reliability, performance, and tests

Key missions

  • Design and operate core runtime services for multi-turn orchestration, tool calling, model routing, memory, streaming, and safety.
  • Own impactful runtime problems end-to-end — from architecture and design to production launch and ongoing reliability.
  • Collaborate closely with product, quality, and application teams to prioritize the most impactful roadmap investments.