Job taxonomy classification

Step 01

Define and Align

Upload sample data, define your output schema, and provide feedback on the hardest cases.

Output schema

RoleChoose one: Role family based on actual responsibilities.
analytics
data_engineering
platform_engineering
solutions_engineering
software_engineering
other
Primary functionChoose one: The work that occupies the role’s primary responsibility.
analysis
data_pipelines
infrastructure
pre_sales
product_development
other
Title alignmentChoose one: Whether the advertised title matches the described work.
aligned
misleading
insufficient_evidence

app.sutro.sh/functions/job-taxonomy-classification

Collecting feedback · 1/3

Map job descriptions to roles using their actual responsibilities.

Example 1 of 3

Title versus duties

Model input

Role title: Data Engineer. Duties: build dashboards, define KPIs, analyze sales; no pipeline work.

Model output

Role

Primary function

Title alignment

Why? Optional guidance

Step 02

Model Sweep

Compare quality and cost on your examples, then choose a model or use Sutro’s default.

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 = {
    "text": "Role title: Data Engineer. Duties: build dashboards, define KPIs, analyze sales; no pipeline work."
}

result = so.run_function(
    "job-taxonomy-classification",
    input_data,
)

curl --fail-with-body -X POST "${SUTRO_API_URL%/}/v1/functions/job-taxonomy-classification/run" \
  -H "Authorization: Key $SUTRO_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "input": {
    "text": "Role title: Data Engineer. Duties: build dashboards, define KPIs, analyze sales; no pipeline work."
  }
}'

Batch

import sutro as so

job_id = so.batch_run_function(
    name="job-taxonomy-classification",
    data="job_taxonomy_classification.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-taxonomy-classification",
  "inputs": [
    {
      "text": "Role title: Data Engineer. Duties: build dashboards, define KPIs, analyze sales; no pipeline work."
    }
  ]
}'