Perplexity

Member of Technical Staff (Software Engineer, Connector Platform)

6.0/10
Perplexity
Not specified
Remote
mid
about 5 hours ago
AI SummaryVerified by Aipplify AI

The vacancy is well-defined in tasks and requirements but lacks compensation details and comprehensive company information.

AI quality score5.9 / 10

Check Match โ€” Just drop your CV

See your fit for Member of Technical Staff (Software Engineer, Connector Platform) in seconds.

Overview

Join Perplexity as a Software Engineer on the Connector Platform team, where you'll build the data layer for integrations, enhancing agent capabilities with reliable and actionable data. The Connector Platform team builds the data layer that lets Perplexity's agents reach into the world's software. This team owns the systems that turn hundreds of heterogeneous integrations (native, MCP, CLI, first-party, and third-party APIs) into one unified, reliable, well-typed surface that agents can call with confidence.

What you'll do

  • โ€ขOwn the design and implementation of the connector runtime, the system that registers, hosts, and executes built-in connectors, hosted MCP servers, and CLI-backed tools behind a single agent-facing interface.
  • โ€ขBuild and extend the semantic layer: tool and entity schemas, capability metadata, relationship modeling, and the mechanisms for capturing and applying organization- and account-specific corrections and knowledge.
  • โ€ขDesign the tool-discovery and tool-selection surfaces that agents use to find the right connector and call it correctly, optimizing for both model accuracy and context efficiency.
  • โ€ขMake agent loops robust: structured results, partial-failure and retry semantics, idempotency, pagination, rate-limit handling, and observability into every tool call an agent makes.
  • โ€ขDefine authentication, authorization, and credential-isolation patterns for connectors (OAuth flows, BYOK, per-org credential boundaries), partnering with Security and Backend Platform on defense-in-depth.
  • โ€ขBuild the connector onboarding path (schemas, fixtures, and evaluation suites) so new connectors ship with measurable quality rather than hope, and drive the eval metrics that tell us a connector actually works inside agent loops.
  • โ€ขSet the technical bar for connector reliability and operability: SLAs, observability, error-rate monitoring, and incident response for an always-on, high-fan-out integration surface.
  • โ€ขPartner with product and AI teams to define clear connector interfaces and integration patterns so new agent capabilities can reliably build on the shared platform.
Loading similar jobs...