Built-in tool

LinkedIn job search

Search LinkedIn job postings by title or keyword, filtered by company, location, workplace, employment type, experience, salary and recency.

10 creditsNo API key needed

Endpoint

Parameters

NameTypeRequiredNote
geoIdstring · optionalstringoptional

LinkedIn Geo ID to filter by. Overrides "location" when set.

salarystring · optionalstringoptional

Filter by minimum base salary (USD).

One of: 40k+, 60k+, 80k+, 100k+, 120k+, 140k+, 160k+, 180k+, 200k+

searchstring · optionalstringoptional

Job title or keywords to search for, e.g. "product manager". Separate several titles with COMMAS to match any of them — "AI engineer, machine learning engineer" is sent as an OR of the two exact phrases. Each phrase is matched as a phrase, not as loose words, so a two-word title will not pull in every posting that happens to contain both words. Boolean syntax is passed straight through if you prefer to write it yourself: `"AI engineer" AND python`, `"AI engineer" NOT intern`. Note sortBy=date returns newest first regardless of how well a posting matches, so use sortBy=relevance when ranking matters more than recency.

Example: product manager

sortBystring · optionalstringoptional

Sort results by relevance or most recent posting date.

One of: relevance, date

locationstring · optionalstringoptional

Filter by ONE LinkedIn-recognized location (e.g. "United States" or "London"). A comma-separated list of countries is not supported. For several locations, make separate bounded searches, starting with the user's priority geography.

One of: United States, London

maxPagesnumber · optionalnumberoptional

Max pages to scrape. Page size depends on the endpoint — read `returned` in the result for the count actually returned, `totalCount` for how many exist and `servableCount` for how many are reachable. Defaults to all pages in Workflows, capped at 100. In chat, returns a preview of ~100 results.

Default: 100

companyIdstring · optionalstringoptional

Filter by LinkedIn company ID. One ID or several comma-separated.

easyApplyboolean · optionalbooleanoptional

Only include jobs that support LinkedIn Easy Apply.

functionIdstring · optionalstringoptional

Filter by LinkedIn job function ID. One ID or several comma-separated.

industryIdstring · optionalstringoptional

Filter by LinkedIn industry ID. One ID or several comma-separated.

postedLimitstring · optionalstringoptional

Only include jobs posted within this recency window.

One of: 24h, week, month

continuationstring · optionalstringoptional

Continuation returned by a previous call. Pass it unchanged with the same search filters to fetch the next batch. Each call has its own paid request budget.

workplaceTypearray · optionalarrayoptional

Filter by workplace type. Choose one or more.

One of: office, hybrid, remote

employmentTypearray · optionalarrayoptional

Filter by employment type. Choose one or more.

One of: full-time, part-time, contract, temporary, internship

experienceLevelarray · optionalarrayoptional

Filter by experience level. Choose one or more. Common API spellings such as entry_level and mid_senior are accepted.

One of: internship, entry, associate, mid-senior, director, executive

under10Applicantsboolean · optionalbooleanoptional

Only include jobs with fewer than 10 applicants.

Response schema

{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "required": [
    "elements"
  ],
  "properties": {
    "hasMore": {
      "type": "boolean",
      "description": "True only when the provider still had reachable data and this execution stopped early. A managed Agent must treat this as an incomplete batch, never as completion."
    },
    "elements": {
      "type": "array",
      "items": {
        "type": "object",
        "required": [
          "id"
        ],
        "properties": {
          "id": {
            "type": "string"
          },
          "url": {
            "type": "string",
            "description": "Direct link to the job listing"
          },
          "title": {
            "type": "string",
            "description": "Title of the position"
          },
          "company": {
            "type": "object",
            "properties": {
              "name": {
                "type": [
                  "string",
                  "null"
                ],
                "description": "Hiring company name. NULL when the vendor has no company for the posting — measured at roughly 1 row in 25, so guard it rather than assuming it is set."
              },
              "linkedinUrl": {
                "type": [
                  "string",
                  "null"
                ],
                "description": "Company page URL. Null when the vendor has no company."
              },
              "universalName": {
                "type": [
                  "string",
                  "null"
                ],
                "description": "URL-friendly company name. Null when the vendor has no company."
              }
            },
            "description": "Hiring company. Always an object on output — the three fields are individually null when the vendor omitted the company, so `company.name` is a safe read.",
            "additionalProperties": true
          },
          "location": {
            "type": "object",
            "properties": {
              "linkedinText": {
                "type": "string",
                "description": "Job location"
              }
            },
            "description": "Location details",
            "additionalProperties": true
          },
          "easyApply": {
            "type": "boolean",
            "description": "Whether quick apply is available"
          },
          "postedDate": {
            "type": "string",
            "description": "When the job was posted"
          }
        },
        "additionalProperties": true
      }
    },
    "nextPage": {
      "type": "integer",
      "exclusiveMinimum": 0
    },
    "returned": {
      "type": "number",
      "description": "How many records this run returned, after any `limit` was applied. ONE EXCEPTION: on a chat preview — where `truncated` is true — this is the count actually FETCHED while `elements` carries only a short sample of them, so the two deliberately disagree. Read `truncated` before comparing this against the array length; in a workflow it is never set and the two always match. Matches the other LinkedIn data tools, whose `meta.returned` is the fetched count on a truncated preview too."
    },
    "truncated": {
      "type": "boolean"
    },
    "stopReason": {
      "enum": [
        "cancelled",
        "provider-error",
        "empty-page-stall",
        "caller-limit",
        "presentation-preview",
        "cursor-stall",
        "runtime-page-window",
        "time-budget"
      ],
      "type": "string"
    },
    "suggestion": {
      "type": "string"
    },
    "totalCount": {
      "type": "number",
      "description": "How many records the search MATCHES, per the provider — the grand total, routinely in the millions while the endpoint will only serve about a thousand of them. Do NOT compare it with the row count to decide whether a run was complete, and do not paginate towards it: use `servableCount` for what is actually reachable. Absent when the provider sent no count."
    },
    "totalPages": {
      "type": "number"
    },
    "pagesScraped": {
      "type": "number"
    },
    "servableCount": {
      "type": "number",
      "description": "How many records this endpoint will serve across all its pages — the real ceiling on what any number of runs can reach, which the provider caps well below `totalCount` on most search endpoints. Absent when the provider sent no count."
    },
    "totalElements": {
      "type": "number",
      "description": "DEPRECATED — despite the name this is the count RETURNED by this run, not a grand total, so it equals your `limit` on a limited run. Kept at that value so existing flows do not change meaning. Use `returned` for this number, `totalCount` for how many records match, or `servableCount` for how many are reachable."
    },
    "nextPaginationToken": {
      "type": "string"
    }
  },
  "additionalProperties": true
}

Get started

How to use this tool

  1. Connect your AI

    Add Connie to ChatGPT, Claude or Slack once, and this tool comes with it. There’s no API key or account to set up.

  2. Ask for the outcome

    Describe what you need in plain words. Your AI runs this tool when the job calls for it, along with any others it needs.

  3. Make it a workflow

    Add it as a step in a workflow that runs the same way every time, on a schedule or when something happens.

  4. Stay in control

    Choose whether it runs on its own or asks first. When it asks, you see an Allow or Deny card before any credits are spent.