Hark
Integration Engineer
San Jose · Full-time
Sponsorship not specified$170k-$400kDetected 83 days ago
GraphQLRESTgRPCOAuthLLMsAgentic AIResearchCommunication
About the role
- That means designing and shipping the protocols, connectors, and execution primitives that let Hark take real actions: reading and writing email, managing calendars, interacting with third-party APIs, and coordinating across services on a user's behalf.
- The power of an agentic system is only as broad as what it can reach.
Responsibilities
- Design and build the integration layer that connects Hark's agent to third-party services, including email, calendar, productivity tools, communication platforms, developer tools, and more.
- Own the full lifecycle of integrations: authentication flows, API clients, schema normalization, action execution, and error handling. Build for reliability, not just the happy path.
- Define and implement the tool and action protocols that let the agent interact with external systems safely and consistently. Make it easy to add new integrations without rewriting the stack.
- Collaborate with model researchers to define tool schemas and action semantics that models can reason about reliably. The quality of the interface shapes model behavior.
- Identify the highest-leverage integrations to prioritize, and drive the roadmap that expands what Hark can do in the world.
- You'll work directly with platform engineers and model researchers, and the integrations you build will define the boundaries of what Hark can do.
- This is a high-ownership role on a small team. You'll work directly with platform engineers and model researchers, and the integrations you build will define the boundaries of what Hark can do.
- You'll build and own the integrations layer that makes Hark's AI agent genuinely useful in the real world.
- Hark is an artificial intelligence company building advanced, personalized intelligence.
- We're pairing that intelligence with next-generation hardware to create a universal interface between humans and machines.
Requirements
- You've shipped connectors to real external services, and you know what breaks in production: auth token expiry, API schema drift, inconsistent error codes, flaky uptime.
- You understand how tool use works in LLM systems, you've thought about how action schemas affect model behavior, and you have opinions about what makes integrations reliable for autonomous agents.
- Comfort with ambiguity and fast iteration.
- You can ship something real quickly, learn from production, and improve without waiting for perfect specs.
Nice to have
- Familiarity with integration standards and protocols such as REST, GraphQL, gRPC, and MCP.
- Experience designing tool-use schemas or function-calling interfaces for LLMs.
- Prior work on developer platforms, integration marketplaces, or iPaaS systems.
- Experience with execution sandboxing or permission-scoped action frameworks.
- Background at a fast-moving AI company or a company where integrations were core to the product.
- The pay offered for this position may vary based on several individual factors, including job-related knowledge, skills, and experience.
- This information will be shared if an employment offer is extended.
- 5+ years of relevant software engineering experience.
Skills
- That means connecting it to the tools, services, and data sources people actually use every day.
Compensation
- The US base salary range for this full-time position is between $170,000 - $400,000 annually.
- The pay offered for this position may vary based on several individual factors, including job-related knowledge, skills, and experience.
- The total compensation package may also include additional components/benefits depending on the specific role.
- This information will be shared if an employment offer is extended.
Benefits
- One that is proactive, multimodal, and capable of interacting with the world through speech, text, vision, and persistent memory.
This listing is sourced directly from Hark's careers page and normalized into a canonical job model.