- Own impactful runtime problems end-to-end - from architecture and design to production launch and ongoing reliability.
- Build and evolve core services for session lifecycle, streaming responses (e.g. gRPC/WebSockets), structured tool execution, memory/state, and policy/guardrails.
- Design for performance correctness cost reduce p50/p95 latency improve tail behavior optimize token/tool budgets.
- Instrument deep observability tracing metrics logs create playbooks/SLOs high availability on-call excellence collaborates closely product quality application teams prioritize roadmap investments available backgrounds which possess strong coding skills Python Go Java C++ focus reliability performance tests operating services Kubernetes cloud AWS Azure event/streaming caching data stores low-latency paths knowledge building blocks tool/function calling outputs model selection/routing debugging OpenTelemetry dashboards production forensics multi-tenant isolation rate-limiting concurrency control optimization certain roles eligible variable compensation equity benefits comprehensive benefits package competitive Medical Vision Dental coverage time-off generous support long-term goals home office improvement annual education wellness stipends vibrant culture events healthy lunches regular diversity bunch people attract retain organization committed inclusive diverse company discriminate gender ethnicity sexual orientation religion civil family status age disability race
-
· About Glean: · Glean is the Work AI platform that helps everyone work smarter with AI. What began as the industry's most advanced enterprise search has evolved into a full-scale Work AI ecosystem, powering intelligent Search, an AI Assistant, and scalable AI agents on one secu ...
San Francisco Bay1 week ago
-
+We're looking for an Agentic AI Infrastructure Engineer to design and scale the systems that power Cloudglue's async agent runtimes, multimodal retrieval pipelines, and large-scale video processing infrastructure. · +Build and evolve async, fault-tolerant runtimes for agentic AI ...
San Francisco1 month ago
-
We're looking for an Agentic AI Infrastructure Engineer to design and scale the systems that power Cloudglue's async agent runtimes, multimodal retrieval pipelines, and large-scale video processing infrastructure. · ...
San Francisco, California, US1 month ago
-
Software Engineer · San Francisco, CA · Full-time · $125,000 base + equity · Ara (YC X26) · About Ara · Ara (YC X26) is building the fastest personal AI agent computing environment, designed to run autonomous agents 24/7. · We provide instant, secure cloud runtimes where agents ...
San Francisco $75,000 - $140,000 (USD) per year5 days ago
-
An opportunity to work from first principles on agentic architectures that power production systems used by professionals globally. · ...
San Francisco, CA3 weeks ago
-
A well-funded AI startup (Series A, · backed by top-tier investors and led by ex-DeepMind / Anthropic / OpenAI · engineers) is building next-generation agentic systems — intelligent, · autonomous software agents that can reason, plan, and act across · browsers, operating systems, ...
San Francisco1 month ago
-
Your Role · The Application Services team plays a critical role in enhancing customer satisfaction and technical collaboration while delivering all application development through a Platform and Technology Product Operating Model. The Full Stack Engineer role will report to the ...
San Francisco $135,000 - $210,000 (USD) per year1 week ago
-
A product-led AI start-up is building one of the most widely adopted AI work companions in the world. · The challenge has shifted to designing agent systems that can plan, reason, evaluate themselves, · and operate reliably inside real products. · ...
San Francisco3 weeks ago
-
Perplexity is looking for a Software Engineer to build the core infrastructure that powers agentic products across Perplexity including Search, Deep Research, and the Comet browser. You will design and evolve the runtime, orchestration, evaluation and training systems that let ag ...
San Francisco $1,200,000 - $1,500,000 (USD) per year1 week ago
-
About Adapt / · Adapt is the AI computer for business. · Develop an agent runtime for orchestrating multi-agent pipelines for data integration and analysis. · Implement server-side logic and APIs with Node to power core product features. · ...
San Francisco, CA1 month ago
-
About Adapt is the AI computer for business that helps every company become instantly AI native through providing a powerful and accessible experience for every job function to collaborate with frontier agents. · Everyone in the company can use Adapt to answer questions, build on ...
San Francisco1 month ago
-
· About LangChain · At LangChain, our mission is to make intelligent agents ubiquitous. We provide the agent engineering platform and open source frameworks developers need to ship reliable agents fast. · Our open source frameworks, LangChain and LangGraph, see over 90 million d ...
San Francisco, CA1 week ago
-
About LangChain · At LangChain, our mission is to make intelligent agents ubiquitous. We build the foundation for agent engineering in the real world, helping developers move from prototypes to production-ready AI agents that teams can rely on. We began as widely adopted open-sou ...
San Francisco, CA2 days ago
-
+Job summary · About Decagon is the leading conversational AI platform empowering every brand to deliver concierge customer experience. · We partner with industry leaders like Hertz Eventbrite Duolingo Oura Bilt Curology and Samsara to redefine customer experience at scale.We're ...
San Francisco $300,000 - $415,000 (USD)1 month ago
-
We are looking for a strong Software Engineer to be part of a high-velocity, high-impact team at the intersection of AI fundamentals, AI infrastructure with an emphasis on systems design.This includes evaluation frameworks and automated integration and load testing embedded in CI ...
San Francisco $171,000 - $190,000 (USD)3 weeks ago
-
+Job summary · The Principal AI Engineer is the lead Architect and hands-on builder of our unified AI Platform as a Service.This role is responsible for transforming raw foundation model capabilities into a scalable, multi-tenant reasoning stack that empowers the entire enterpris ...
San Francisco2 weeks ago
-
About the Team · With Codex we're building an AI software engineer. One that you can pair with, delegate to, or even ask to take on future tasks proactively. Our team is a fast-moving group within OpenAI, bringing together research, engineering, design, and product. We iterativel ...
San Francisco1 week ago
-
About The Team · With Codex we're building an AI software engineer. One that you can pair with, delegate to, or even ask to take on future tasks proactively. Our team is a fast-moving group within OpenAI, bringing together research, engineering, design, and product. We iterativel ...
San Francisco, CA1 week ago
-
We build an AI software engineer. One that you can pair with delegate to or even ask to take on future tasks proactively. · The Codex team is responsible for building state-of-the-art AI systems that can write code reason about software and act as intelligent agents for developer ...
San Francisco $230,000 - $325,000 (USD)1 month ago
-
About Us: · At LangChain, our mission is to make intelligent agents ubiquitous. We build the foundation for agent engineering in the real world, helping developers move from prototypes to production-ready AI agents that teams can rely on. We began as widely adopted open-source to ...
San Francisco, CA10 hours ago
-
About Decagon · Decagon is the leading conversational AI platform empowering every brand to deliver concierge customer experiences. · Our technology enables industry-defining enterprises like Avis Budget Group, Block's Cash App and Square, Chime, Oura Health, and Hunter Douglas t ...
San Francisco10 hours ago
Software Engineer, Agentic Runtime - San Francisco - Glean
Description
About Glean
Glean is the Work AI platform that helps everyone work smarter with AI.
What began as the industry's most advanced enterprise search has evolved into a full-scale Work AI ecosystem, powering intelligent Search, an AI Assistant, and scalable AI agents on one secure, open platform.
The Agents Runtime Team
-
Software Engineer, Agentic Runtime
Only for registered members San Francisco Bay
-
Founding Agentic AI Infrastructure Engineer
Only for registered members San Francisco
-
Founding Agentic AI Infrastructure Engineer
Only for registered members San Francisco, California, US
-
Software Engineer
Only for registered members San Francisco
-
Agentic AI Engineer
Only for registered members San Francisco, CA
-
Machine Learning Engineer
Only for registered members San Francisco
-
Full Stack Engineer, Senior
Only for registered members San Francisco
-
Agentic AI Engineer
Only for registered members San Francisco
-
Software Engineer
Only for registered members San Francisco
-
Customer Facing Full Stack Engineer
Only for registered members San Francisco, CA
-
Customer Facing Full Stack Engineer
Only for registered members San Francisco
-
Senior Backend Engineer, LangSmith Deployments
Only for registered members San Francisco, CA
-
Senior Backend Engineer, LangSmith Deployments
Only for registered members San Francisco, CA
-
Engineering Manager, Agent Orchestration
Only for registered members San Francisco
-
Software Engineer II
Only for registered members San Francisco
-
Pricipal AI Engineer
Only for registered members San Francisco
-
Software Engineer, Codex Cloud
Only for registered members San Francisco
-
Software Engineer, Codex Cloud
Only for registered members San Francisco, CA
-
Software Engineer, Codex Cloud
Only for registered members San Francisco
-
Python OSS Engineer
Only for registered members San Francisco, CA
-
Engineering Manager, Agent Orchestration
Only for registered members San Francisco