{ "feed": "jobs", "version": 1, "publisher": "Arcadium Data", "layout": "//dt=YYYY-MM-DD/part-.{parquet,jsonl.gz}", "formats": { "parquet": "Parquet, zstd, one row group per 50k rows", "jsonl_gz": "JSON Lines, gzip; timestamps as ISO 8601 UTC" }, "cuts": [ { "id": "global", "dir": "global", "label": "All jobs" }, { "id": "eu", "dir": "region=eu", "label": "Jobs located in Europe (EU-27, EEA, UK, Switzerland)" }, { "id": "us", "dir": "region=us", "label": "Jobs located in the United States" }, { "id": "remote", "dir": "remote_only", "label": "Fully remote jobs (any country)" } ], "europe_countries": [ "AT", "BE", "BG", "CH", "CY", "CZ", "DE", "DK", "EE", "ES", "FI", "FR", "GB", "GR", "HR", "HU", "IE", "IS", "IT", "LI", "LT", "LU", "LV", "MT", "NL", "NO", "PL", "PT", "RO", "SE", "SI", "SK" ], "personal_data": "none: no recruiter or contact names, emails or phone numbers; text fields pass a PII filter", "tables": { "jobs_delta": { "cadence": "daily (one part per run; several parts in a dt partition are all valid and ordered by name)", "description": "Jobs that entered, changed in or left the cut since the previous run. Append-only.", "columns": [ { "name": "change_type", "type": "STRING", "nullable": false, "description": "`new` (job enters this cut), `updated` (content_hash changed, or a closed job reopened), `closed` (job left this cut)." }, { "name": "removal_reason", "type": "STRING", "nullable": true, "description": "For `closed` rows: closed (gone from the board), duplicate (same job found on another source), excluded (employer now out of scope, e.g. a staffing agency), deleted (board removed), left_cut (still open, no longer in this cut)." }, { "name": "job_id", "type": "STRING", "nullable": false, "description": "Stable job id `___`; the key of every delta row." }, { "name": "title", "type": "STRING", "nullable": false, "description": "Job title as posted (emails, phone numbers and personal profile links removed)." }, { "name": "company_name", "type": "STRING", "nullable": true, "description": "Employer display name (cleaned; careers-page slogans dropped)." }, { "name": "company_domain", "type": "STRING", "nullable": true, "description": "Employer website domain, lower case, without www (null when not matched with confidence)." }, { "name": "country", "type": "STRING", "nullable": true, "description": "Primary country, ISO 3166-1 alpha-2 (first of `countries`)." }, { "name": "countries", "type": "STRING", "nullable": true, "description": "All countries of the job locations, ISO alpha-2, `;`-separated." }, { "name": "locations", "type": "STRING", "nullable": true, "description": "Location texts as posted, `;`-separated." }, { "name": "remote", "type": "BOOLEAN", "nullable": true, "description": "true = fully remote, false = on-site or hybrid, null = not stated." }, { "name": "employment_type", "type": "STRING", "nullable": true, "description": "Employment type as stated by the ATS (full-time, part-time, contract ...)." }, { "name": "seniority", "type": "STRING", "nullable": true, "description": "Seniority level when the ATS states one." }, { "name": "department", "type": "STRING", "nullable": true, "description": "Primary department or team (first of `departments`)." }, { "name": "departments", "type": "STRING", "nullable": true, "description": "All departments or teams, `;`-separated." }, { "name": "salary_min", "type": "DOUBLE", "nullable": true, "description": "Lower pay bound, only when the posting states pay in a structured field or a clear text range." }, { "name": "salary_max", "type": "DOUBLE", "nullable": true, "description": "Upper pay bound (same rule)." }, { "name": "salary_currency", "type": "STRING", "nullable": true, "description": "ISO 4217 currency of the pay range." }, { "name": "salary_period", "type": "STRING", "nullable": true, "description": "Pay period of the range (year, month, hour ...)." }, { "name": "salary_source", "type": "STRING", "nullable": true, "description": "Where the pay range came from (structured ATS field or posting text)." }, { "name": "ats", "type": "STRING", "nullable": false, "description": "Source system the job was read from (greenhouse, lever, workday, smartrecruiters, ...)." }, { "name": "language", "type": "STRING", "nullable": true, "description": "Language of the posting when known (ISO 639-1)." }, { "name": "posted_at", "type": "TIMESTAMP", "nullable": true, "description": "Posting date stated by the employer (UTC); null when the ATS gives none." }, { "name": "updated_at", "type": "TIMESTAMP", "nullable": true, "description": "Last update stated by the employer (UTC)." }, { "name": "first_seen_at", "type": "TIMESTAMP", "nullable": false, "description": "When we first saw the job (UTC). Point-in-time stamp: never moves." }, { "name": "last_seen_at", "type": "TIMESTAMP", "nullable": false, "description": "Last crawl that still saw the job open (UTC)." }, { "name": "closed_at", "type": "TIMESTAMP", "nullable": true, "description": "When the job disappeared from the employer board (UTC); null while open." }, { "name": "url", "type": "STRING", "nullable": false, "description": "Public job posting URL on the employer careers site or ATS." }, { "name": "content_hash", "type": "STRING", "nullable": false, "description": "Hash of the exported fields except `last_seen_at` and `description`; changes = an `updated` delta row." }, { "name": "description", "type": "STRING", "nullable": true, "description": "Full job description, plain text (only in feeds built with --with-descriptions; off by default)." } ] }, "jobs_snapshot": { "cadence": "weekly (and on the first run)", "description": "Every open job of the cut at export time. One part per dt partition.", "columns": [ { "name": "job_id", "type": "STRING", "nullable": false, "description": "Stable job id `___`; the key of every delta row." }, { "name": "title", "type": "STRING", "nullable": false, "description": "Job title as posted (emails, phone numbers and personal profile links removed)." }, { "name": "company_name", "type": "STRING", "nullable": true, "description": "Employer display name (cleaned; careers-page slogans dropped)." }, { "name": "company_domain", "type": "STRING", "nullable": true, "description": "Employer website domain, lower case, without www (null when not matched with confidence)." }, { "name": "country", "type": "STRING", "nullable": true, "description": "Primary country, ISO 3166-1 alpha-2 (first of `countries`)." }, { "name": "countries", "type": "STRING", "nullable": true, "description": "All countries of the job locations, ISO alpha-2, `;`-separated." }, { "name": "locations", "type": "STRING", "nullable": true, "description": "Location texts as posted, `;`-separated." }, { "name": "remote", "type": "BOOLEAN", "nullable": true, "description": "true = fully remote, false = on-site or hybrid, null = not stated." }, { "name": "employment_type", "type": "STRING", "nullable": true, "description": "Employment type as stated by the ATS (full-time, part-time, contract ...)." }, { "name": "seniority", "type": "STRING", "nullable": true, "description": "Seniority level when the ATS states one." }, { "name": "department", "type": "STRING", "nullable": true, "description": "Primary department or team (first of `departments`)." }, { "name": "departments", "type": "STRING", "nullable": true, "description": "All departments or teams, `;`-separated." }, { "name": "salary_min", "type": "DOUBLE", "nullable": true, "description": "Lower pay bound, only when the posting states pay in a structured field or a clear text range." }, { "name": "salary_max", "type": "DOUBLE", "nullable": true, "description": "Upper pay bound (same rule)." }, { "name": "salary_currency", "type": "STRING", "nullable": true, "description": "ISO 4217 currency of the pay range." }, { "name": "salary_period", "type": "STRING", "nullable": true, "description": "Pay period of the range (year, month, hour ...)." }, { "name": "salary_source", "type": "STRING", "nullable": true, "description": "Where the pay range came from (structured ATS field or posting text)." }, { "name": "ats", "type": "STRING", "nullable": false, "description": "Source system the job was read from (greenhouse, lever, workday, smartrecruiters, ...)." }, { "name": "language", "type": "STRING", "nullable": true, "description": "Language of the posting when known (ISO 639-1)." }, { "name": "posted_at", "type": "TIMESTAMP", "nullable": true, "description": "Posting date stated by the employer (UTC); null when the ATS gives none." }, { "name": "updated_at", "type": "TIMESTAMP", "nullable": true, "description": "Last update stated by the employer (UTC)." }, { "name": "first_seen_at", "type": "TIMESTAMP", "nullable": false, "description": "When we first saw the job (UTC). Point-in-time stamp: never moves." }, { "name": "last_seen_at", "type": "TIMESTAMP", "nullable": false, "description": "Last crawl that still saw the job open (UTC)." }, { "name": "closed_at", "type": "TIMESTAMP", "nullable": true, "description": "When the job disappeared from the employer board (UTC); null while open." }, { "name": "url", "type": "STRING", "nullable": false, "description": "Public job posting URL on the employer careers site or ATS." }, { "name": "content_hash", "type": "STRING", "nullable": false, "description": "Hash of the exported fields except `last_seen_at` and `description`; changes = an `updated` delta row." }, { "name": "description", "type": "STRING", "nullable": true, "description": "Full job description, plain text (only in feeds built with --with-descriptions; off by default)." } ] }, "companies_signals": { "cadence": "daily; every day is kept (the history is the asset). The latest two days are rewritten as they settle.", "description": "One row per company and day: open jobs, 7/30-day hiring change, openings, closures, market entries, remote and pay shares, department mix shift, tech stack and event counts.", "columns": [ { "name": "company_domain", "type": "STRING", "nullable": false, "description": "Company website domain (the company key)." }, { "name": "company_name", "type": "STRING", "nullable": true, "description": "Employer display name." }, { "name": "as_of", "type": "STRING", "nullable": false, "description": "Day the signals describe (UTC, YYYY-MM-DD); equals the dt partition." }, { "name": "provisional", "type": "BOOLEAN", "nullable": true, "description": "true while the company has under 28 days of history: trend columns are not final yet." }, { "name": "history_days", "type": "INT64", "nullable": true, "description": "Days since the company was first tracked." }, { "name": "ats", "type": "STRING", "nullable": true, "description": "Source systems of the company boards, `;`-separated." }, { "name": "boards", "type": "INT64", "nullable": true, "description": "Number of job boards folded into the company." }, { "name": "open_jobs", "type": "INT64", "nullable": false, "description": "Open jobs at the end of the day." }, { "name": "net_change_7d", "type": "INT64", "nullable": true, "description": "Open jobs now minus 7 days ago (boards tracked on both days); null until 7 days of history." }, { "name": "net_change_30d", "type": "INT64", "nullable": true, "description": "Open jobs now minus 30 days ago; null until 30 days of history." }, { "name": "change_7d_pct", "type": "DOUBLE", "nullable": true, "description": "net_change_7d / open jobs 7 days ago." }, { "name": "openings_7d", "type": "INT64", "nullable": true, "description": "Jobs posted in the 7 days to as_of." }, { "name": "openings_30d", "type": "INT64", "nullable": true, "description": "Jobs posted in the 30 days to as_of." }, { "name": "closures_7d", "type": "INT64", "nullable": true, "description": "Jobs that disappeared in the 7 days to as_of." }, { "name": "closures_30d", "type": "INT64", "nullable": true, "description": "Jobs that disappeared in the 30 days to as_of." }, { "name": "countries", "type": "INT64", "nullable": true, "description": "Countries with open jobs." }, { "name": "cities", "type": "INT64", "nullable": true, "description": "Cities with open jobs." }, { "name": "new_countries_30d", "type": "INT64", "nullable": true, "description": "Countries entered in the 30 days to as_of (market entries)." }, { "name": "new_cities_30d", "type": "INT64", "nullable": true, "description": "Cities entered in the 30 days to as_of." }, { "name": "remote_share", "type": "DOUBLE", "nullable": true, "description": "Share of open jobs that are fully remote." }, { "name": "remote_share_change_30d", "type": "DOUBLE", "nullable": true, "description": "Change of remote_share against ~30 days ago." }, { "name": "posted_pay_share", "type": "DOUBLE", "nullable": true, "description": "Share of open jobs that state pay." }, { "name": "ghost_share", "type": "DOUBLE", "nullable": true, "description": "Share of open jobs posted (or first seen) over 90 days ago." }, { "name": "top_department", "type": "STRING", "nullable": true, "description": "Department with the most open jobs." }, { "name": "department_shift_30d", "type": "DOUBLE", "nullable": true, "description": "Total variation distance of the department mix against ~30 days ago (0-1)." }, { "name": "top_country", "type": "STRING", "nullable": true, "description": "Country with the most open jobs (ISO alpha-2)." }, { "name": "tech_tools", "type": "INT64", "nullable": true, "description": "Number of tools named in the open job posts (tech stack)." }, { "name": "top_tech", "type": "STRING", "nullable": true, "description": "Most named tools, `;`-separated." }, { "name": "events_30d", "type": "STRING", "nullable": true, "description": "Hiring-change events in the 30 days to as_of, `type:count;...` (market_entry, ats_switch, hiring_surge, hiring_freeze, new_department)." } ] } } }