Instabase provides a cloud platform that extracts, classifies, and analyzes unstructured documents, offers OCR/NLP and generative AI tools, and deploys customizable workflow apps and a prebuilt-app marketplace.
<div class="content-intro"><p><span style="font-weight: 400;">At Instabase, we're passionate about democratizing access to cutting-edge AI innovation to enable any organization to solve previously unsolvable unstructured data problems in their industry. With customers representing some of the largest and most complex organizations in the world, and investors like Greylock, Andreessen Horowitz, and Index Ventures, our market opportunity is near infinite.</span></p> <p><span style="font-weight: 400;">Instabase offers a consumption-based pricing model where customers can pay only for what they use, aligning directly with the value our products deliver. It empowers our clients to explore our AI Hub platform features extensively, enabling them to uncover crucial business insights. This customer-centric model allows Instabase to glean insights from diverse use cases and behaviors, ensuring we deliver top-tier solutions that provide unmatched advantages for everyday business operations.</span></p> <p><span style="font-weight: 400;">With offices in San Francisco and Bengaluru, Instabase is a truly global company. We are <strong>people-first</strong>, and we've built a fearlessly experimental, endlessly curious, customer obsessed team who work together and help organizations around the world turn their unstructured data into insights instantly.</span></p></div><h2>About Instabase & SuperApp</h2> <p>Instabase is on a mission to democratize access to cutting-edge AI innovation, enabling organizations to solve previously unsolvable unstructured data problems.</p> <p><strong>SuperApp</strong> is our flagship AI agent workspace. It unifies communication, collaboration, file sharing, and multimodal reasoning into a single, seamless platform. Powering SuperApp is our <strong>Agent Harness</strong>—the underlying execution engine that manages agent states, orchestrates multi-turn planning and tool execution, enforces strict security guardrails, and runs untrusted, dynamic code in secure, sandboxed environments.</p> <p>As a Staff AI Engineer on the Agent Harness team, you will design the foundation of this runtime execution environment, enabling SuperApp to act as a resilient, highly scalable, and ultra-secure agentic operating system for the enterprise.</p> <hr> <h2>Role Overview</h2> <p>We are seeking a visionary systems-minded AI engineer to lead the design, architecture, and development of the <strong>Agent Harness</strong>. In this role, you will bridge the gap between advanced foundation models (LLMs) and reliable, production-grade execution.</p> <p>You will not just be "vibe coding" prompts ; you will build the actual state machine, execution sandbox, tool-calling middleware, and security containment layers that allow AI agents to safely execute code, search the web, manipulate files, and query databases in real-time. This is a high-leverage role requiring deep expertise in distributed backend systems, runtime isolation, and stateful agent choreography. </p> <hr> <h2>What You’ll Do (Responsibilities)</h2> <ul> <li><strong>Harness Architecture & State Management:</strong> Architect the next-generation execution runtime (Agent Harness) that drives SuperApp’s planning, reasoning, memory retention, and tool-execution loops. Build reliable state machines capable of pausing, resuming, and versioning agent trajectories.</li> <li><strong>Secure Sandbox Execution:</strong> Design and scale highly secure, isolated, and ephemeral environments (using Docker, gVisor, WebAssembly, or microVMs) to execute agent-generated code safely without putting host infrastructure at risk.</li> <li><strong>Tool & Integration Frameworks:</strong> Build and maintain high-throughput APIs and integration layers (such as the Model Context Protocol - MCP) that connect SuperApp to external services, databases, web search utilities, and complex file processors.</li> <li><strong>Security & Guardrail Engineering:</strong> Engineer robust system-level guardrails to detect and mitigate prompt injection, defend against jailbreak attempts, and ensure strict compliance with system prompt instructions and data isolation boundaries.</li> <li><strong>Performance & Context Optimization:</strong> Implement advanced routing, context window pruning, and context caching strategies to optimize LLM token usage, minimize round-trip latencies, and drastically reduce the operational cost of complex agent loops.</li> <li><strong>Technical Strategy & Mentorship:</strong> Write comprehensive high-level design documents, align cross-functional engineering teams on the technical roadmap, and mentor senior and mid-level software engineers across the organization.</li> </ul> <hr> <h2>About You</h2> <ul> <li><strong>Experience:</strong> Minimum <strong>6+ years</strong> of professional software engineering experience, with a proven track record of designing, scaling, and operating mission-critical distributed systems.</li> <li><strong>Agentic AI Expertise:</strong> <strong>2+ years</strong> of production experience building or modifying agent execution environments, LLM orchestrators, or tool-calling frameworks (e.g., custom runtimes, LangChain, AutoGen, or similar systems).</li> <li><strong>Backend Mastery:</strong> Expert proficiency in <strong>Go and Python</strong>. You have a pragmatic, deep understanding of concurrent programming, microservices, gRPC, and highly scalable API design.</li> <li><strong>Runtime Isolation & Security:</strong> Strong experience with containerization and virtualization technologies (Docker, Kubernetes) and a solid grasp of sandboxing untrusted code execution.</li> <li><strong>Distributed Systems Fundamentals:</strong> Deep familiarity with message brokers (e.g., Kafka, RabbitMQ), caching infrastructure (Redis), and relational/non-relational database design.</li> <li><strong>Education:</strong