SlipstreamJobs tracks this role from the company's public career site. Apply directly on the employer's site.
Salary: USD 180,000 - 210,000 / annual
Glean is a Work AI platform that helps enterprises work smarter with AI through intelligent search, an AI assistant, and scalable AI agents. The company powers agentic capabilities across 1,000+ employees in 25+ countries, serving customers across 50+ industries.
The Agentic Runtime team builds the low-latency, reliable, and secure foundation powering Glean's AI agents and assistant experiences at scale. This role focuses on designing and operating core runtime services for multi-turn orchestration, tool calling, model routing, memory, streaming, and safety.
Key responsibilities include:
- Own impactful runtime problems end-to-end from architecture and design through production launch and ongoing reliability
- Build and evolve core services for session lifecycle, streaming responses (gRPC/WebSockets), structured tool execution, memory/state, and policy/guardrails
- Design for performance, correctness, and cost: reduce p50/p95 latency, improve tail behavior, and optimize token/tool budgets
- Integrate with leading LLM providers (OpenAI, Anthropic, Google Gemini) and internal evaluation frameworks
- Harden the platform with fault isolation, retries, timeouts, circuit-breaking, backpressure, and graceful degradation
- Instrument deep observability (tracing, metrics, logs) and create playbooks/SLOs for high availability and on-call excellence
- Collaborate with product, quality, and application teams to prioritize roadmap investments
Requirements:
- 3+ years of software engineering experience building production distributed systems or cloud-native applications
- BS/BA in Computer Science or related field, or equivalent practical experience
- Strong coding skills in at least one of: Python, Go, Java, Javascript, Typescript, C++, with focus on reliability, performance, and tests
- Product-minded: prioritize customer impact, clear SLAs/SLOs, and pragmatic iteration
- Ownership-driven with positive, proactive attitude; comfortable leading projects or learning from experienced engineers
Preferred qualifications:
- Experience operating services on Kubernetes and at least one major cloud (GCP, AWS, or Azure)
- Familiarity with event/streaming systems (Pub/Sub, Kafka), caching (Redis), and data stores for low-latency paths
- Practical understanding of LLM/agents building blocks: tool/function calling, structured outputs, streaming, and model selection/routing
- Strong observability and debugging skills: tracing (OpenTelemetry), metrics, dashboards, and production forensics
- Background in policy/guardrails, multi-tenant isolation, rate-limiting, concurrency control, or cost optimization
