Member of Technical Staff (Software Engineer, Connector Platform)

Details

The Connector Platform team builds the data layer that enables Perplexity's agents to access the world's software. The team owns systems that turn hundreds of heterogeneous integrations—including native, MCP, CLI, first-party, and third-party APIs—into one unified, reliable, well-typed surface that agents can use confidently.

The connector platform is the core knowledge layer for Computer. It enables agents to discover available tools, understand their capabilities, determine which tools to call, and ground their reasoning in real, permissioned, up-to-date enterprise data. The team maintains a knowledge layer above connectors that pushes and pulls context into them, making Computer the source of truth for institutional knowledge.

Responsibilities

• Own the design and implementation of the connector runtime, which registers, hosts, and executes built-in connectors, hosted MCP servers, and CLI-backed tools behind a single agent-facing interface.
• Build and extend the semantic layer, including tool and entity schemas, capability metadata, relationship modeling, and mechanisms for capturing and applying organization- and account-specific corrections and knowledge.
• Design tool-discovery and tool-selection surfaces that agents use to find the right connector and call it correctly, optimizing for model accuracy and context efficiency.
• Make agent loops robust through structured results, partial-failure and retry semantics, idempotency, pagination, rate-limit handling, and observability into every tool call.
• Define authentication, authorization, and credential-isolation patterns for connectors, including OAuth flows, BYOK, and per-organization credential boundaries, in partnership with Security and Backend Platform.
• Build the connector onboarding path, including schemas, fixtures, and evaluation suites, so new connectors ship with measurable quality.
• Drive evaluation metrics that demonstrate whether connectors work effectively inside agent loops.
• Set the technical bar for connector reliability and operability, including SLAs, observability, error-rate monitoring, and incident response for an always-on, high-fan-out integration surface.
• Partner with product and AI teams to define clear connector interfaces and integration patterns so new agent capabilities can reliably build on the shared platform.

Requirements

• Experience designing and building backend systems that run in production, typically 4+ years for mid-level roles and more for senior and staff roles.
• Strong system design skills and a track record of building efficient, reliable, and scalable architectures, ideally including API integration, gateway, or platform-style systems with many heterogeneous downstreams.
• Strong proficiency in at least one backend language such as Python, Go, or Rust, with the ability to work effectively in a multi-language environment.
• Hands-on experience with modern infrastructure such as AWS, Kubernetes, and related cloud technologies.
• Depth in at least one of the following areas: OAuth and authorization protocols; API, connector, or MCP-server development; schema and semantic modeling; or tooling and evaluation for LLM-based agents.
• Comfort working in security-sensitive areas, including authentication, authorization, and credential isolation, while making pragmatic trade-offs between safety, simplicity, and velocity.
• A collaborative mindset and eagerness to solve hard, ambiguous problems alongside experienced engineers.
• Applicants are encouraged to apply even if their experience does not match every listed qualification.

Benefits

• Equity.
• Comprehensive benefits for full-time U.S. employees, including health, dental, vision, retirement, fitness, commuter, and dependent care accounts.
• International benefits tailored to the employee's region of residence.