Software Engineer, Agentic Runtime

Details

Glean is the Work AI platform helping organizations work smarter with AI. Its platform includes enterprise search, an AI Assistant, scalable AI agents, over 100 enterprise SaaS connectors, flexible LLM choice, robust APIs, and enterprise and personal knowledge graphs.

The Agentic Runtime team builds the low-latency, reliable, and secure foundation powering Glean's AI agents and assistant experiences at scale. The role involves designing and operating core runtime services for multi-turn orchestration, tool calling, model routing, memory, streaming, and safety across distributed systems and ML infrastructure integrations.

Responsibilities

• 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 such as gRPC and WebSockets, structured tool execution, memory and state, and policy and guardrails.
• Design for performance, correctness, and cost by reducing p50 and p95 latency, improving tail behavior, and optimizing token and tool budgets.
• Integrate with leading LLM providers such as OpenAI, Anthropic, and Google Gemini, as well as internal evaluation frameworks.
• Improve platform resilience through fault isolation, retries, timeouts, circuit breaking, backpressure, and graceful degradation.
• Instrument deep observability through tracing, metrics, and logs, and create playbooks and SLOs for high availability and on-call excellence.
• Collaborate with product, quality, and application teams to prioritize impactful roadmap investments.

Requirements

• 3+ years of software engineering experience building production distributed systems or cloud-native applications.
• Bachelor's degree in Computer Science or a related field, or equivalent practical experience.
• Strong coding skills in at least one of Python, Go, Java, JavaScript, TypeScript, or C++, with a focus on reliability, performance, and testing.
• Product-minded approach with an emphasis on customer impact, clear SLAs and SLOs, and pragmatic iteration.
• Ownership-driven, positive, and proactive attitude, with the ability to lead projects or learn from experienced engineers.
• Experience operating services on Kubernetes and at least one major cloud platform, such as GCP, AWS, or Azure.
• Familiarity with event and streaming systems such as Pub/Sub and Kafka, caching systems such as Redis, and data stores for low-latency paths.
• Practical understanding of LLM and agent building blocks, including tool and function calling, structured outputs, streaming, and model selection and routing.
• Strong observability and debugging skills, including tracing with tools such as OpenTelemetry, metrics, dashboards, and production forensics.
• Experience in policy and guardrails, multi-tenant isolation, rate limiting, concurrency control, or cost optimization is a plus.

Location

• Hybrid role requiring four days per week in the Mountain View office.

Compensation And Benefits

• Standard base salary range of $180,000–$210,000 annually.
• Certain roles may be eligible for variable compensation, equity, and benefits.
• Medical, vision, and dental coverage.
• Generous time-off policy.
• 401(k) plan.
• Home office improvement stipend.
• Annual education and wellness stipends.
• Regular company events and healthy lunches daily.

Glean is committed to an inclusive and diverse workplace and does not discriminate based on gender, ethnicity, sexual orientation, religion, civil or family status, age, disability, or race. As part of the interview process, candidates complete a brief AI-focused exercise or discussion covering how they think about, design, and use AI. The posting also includes a global data privacy notice for job candidates and applicants.