Extract job posting data

Step 01

Define and Align

Review draft extractions and explain which source details to preserve or correct.

Output schema

Job titleText: The role title stated in the posting.
LocationText: Role-specific location, rather than company headquarters. Not provided when absent from the source.
Remote scopeText: Geographic and office-attendance restrictions on remote work. Not provided when absent from the source.
Salary base minNumber · optional: Minimum base salary; not provided when absent.
Salary base maxNumber · optional: Maximum base salary, excluding commission and OTE; not provided when absent.
CurrencyText · optional: Three-letter currency code for the stated base salary. Not provided when absent from the source.

app.sutro.sh/functions/job-posting-extraction

Collecting feedback · 1/3

Extract structured job information from the supplied posting.

Example 1 of 3

Remote role · geographic limits

Model input

“Data Engineer. Remote within Germany only. Company headquarters: London.”

Model output

Job title

Location

Remote scope

Salary base min

Salary base max

Currency

Why? Optional guidance

Step 02

Model Sweep

Compare models on your extraction examples and choose a tradeoff.

Compare models on expert agreement and cost. The interactive chart uses illustrative measurements.

Illustrative sweep · select Value or Best to use that model in your function.

Step 03

Deployment

Call Sutro Functions like any other software. Swap the model as soon as something more performant is released.

Selected modelWaiting for sweep results.

Real-time

import sutro as so

input_data = {
    "posting": "Data Engineer. Remote within Germany only. Headquarters: London. Salary not listed."
}

result = so.run_function(
    "job-posting-extraction",
    input_data,
)

curl --fail-with-body -X POST "${SUTRO_API_URL%/}/v1/functions/job-posting-extraction/run" \
  -H "Authorization: Key $SUTRO_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "input": {
    "posting": "Data Engineer. Remote within Germany only. Headquarters: London. Salary not listed."
  }
}'

Batch

import sutro as so

job_id = so.batch_run_function(
    name="job-posting-extraction",
    data="collected_job_postings.csv",
)
results = so.await_job_completion(job_id)

curl --fail-with-body -X POST "${SUTRO_API_URL%/}/v1/batch-inference" \
  -H "Authorization: Key $SUTRO_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "job-posting-extraction",
  "inputs": [
    {
      "posting": "Data Engineer. Remote within Germany only. Headquarters: London. Salary not listed."
    }
  ]
}'