Occupation resolver
Employer data is the most detailed record of the labor market there is, but it is of little use until every messy title is mapped to one code. The resolver runs cheap checks first, calls models where they are needed, and sends what it cannot match to review.
The problem
Employers name the same job a hundred ways, from "AmbFloat LPN / II" to "RN/Care Manager" and "Sr. Scrum Master (Remote, LOCALS)". Until those titles are mapped to one federal taxonomy, there is no way to benchmark, forecast or trace career transitions. There is also no ground truth to check against, since no labeled set says which code is correct. Everything after this stage depends on getting it right cheaply and reliably.
How it works
01One job, a hundred names
Raw titles carry shift tags, unit codes, seniority markers and location suffixes, which have to be removed before the title can be judged. The first stage strips and normalizes the input so that what remains describes the job.
02Cheapest checks first
A ten-stage cascade resolves what it can at each step and passes the rest on, starting with exact caches and keyword rules, then substring and embedding matches, then the models. Each stage has a confidence floor, and no match below it is accepted.
03Three models, called in sequence
An open-source embedding baseline handles most titles at no cost. A fine-tuned in-domain encoder handles the ambiguous middle. A local, tenant-isolated LLM decides the long tail of novel titles, marketing language and compound roles, with output constrained to JSON.
04Labels without a labeled set
With no gold standard to train on, a locally run LLM generates labels over normalized employer extracts, and those labels are then reviewed. That turns an unlabeled problem into a supervised one at scale, and the in-domain encoder is trained on the result.
Each title is resolved two ways at once. On the left, a clean employer role with its specialty, level, and grade. On the right, the federal occupation at O*NET 8-digit and SOC-6, with its family and subfamily.
Two scrubbed samples run through the resolver. Each messy input is shown with the standard role and the federal occupation it maps to. Switch between the contributed employer panel and public postings.
| Original title | Canonical | Specialty | Level | SOC-6 | SOC-6 title | Family |
|---|---|---|---|---|---|---|
| AmbFloat LPN / II | LPN | · | staff | 29-2061 | Licensed Practical and Licensed Vocational Nurses | Health Technologists and Technicians |
| Certified Nursing Assistant I - B1D Critical Care 1st Floor | Nurse Aide | Critical Care | staff | 31-1131 | Nursing Assistants | Home Health and Personal Care Aides; and Nursing Assistants, Orderlies, and Psychiatric Aides |
| CRNA ( Only) | CRNA | · | staff | 29-1151 | Nurse Anesthetists | Healthcare Diagnosing or Treating Practitioners |
| DevOps Engineer-Software Engineer III, Enterprise Risk Finance Technology | Software Engineer | DevOps | staff | 15-1252 | Software Developers | Computer Occupations |
| Clinical Staff Pharmacist Pharmacy and ED | Clinical Pharmacist | · | staff | 29-1051 | Pharmacists | Healthcare Diagnosing or Treating Practitioners |
| Senior Industrial Engineer | Industrial Engineer | · | senior | 17-2112 | Industrial Engineers | Engineers |
| Biomedical Equipment Tech Senior | Biomedical Equipment Tech | · | senior | 49-9062 | Medical Equipment Repairers | Other Installation, Maintenance, and Repair Occupations |
| Senior Credit Analyst | Credit Analyst | · | senior | 13-2041 | Credit Analysts | Financial Specialists |
| Physical Therapist Assistant (Licensed) - Outpatient Rehab | Physical Therapist Assistant | Outpatient | staff | 31-2021 | Physical Therapist Assistants | Occupational Therapy and Physical Therapist Assistants and Aides |
| Telecomm Technician Senior | Telecommunications Equipment Installer and Repairer | · | senior | 49-2022 | Telecommunications Equipment Installers and Repairers, Except Line Installers | Electrical and Electronic Equipment Mechanics, Installers, and Repairers |
| Supervisor Health Information Management | Health Information Management Supervisor | · | supervisor | 29-2072 | Medical Records Specialists | Health Technologists and Technicians |
| Respiratory Therapist II (RRT) ( Only) | Respiratory Therapist | · | staff | 29-1126 | Respiratory Therapists | Healthcare Diagnosing or Treating Practitioners |
| NonEE) Accounts Payable Associate | Accounts Payable Associate | · | staff | 43-3021 | Billing and Posting Clerks | Financial Clerks |
| Associate Customer Service Representative | Customer Service Representative | · | staff | 43-4051 | Customer Service Representatives | Information and Record Clerks |
| Customer Tax Associate | Tax Associate | · | staff | 13-2082 | Tax Preparers | Financial Specialists |
| Digitial Marketing Manager II | Digital Marketing Manager | · | manager | 11-2021 | Marketing Managers | Advertising, Marketing, Promotions, Public Relations, and Sales Managers |
| Director Neonatal Nurse Practitioner | Neonatal Nurse Practitioner | · | manager | 29-1171 | Nurse Practitioners | Healthcare Diagnosing or Treating Practitioners |
| Early Career Senior Learning and Development Consultant | Learning and Development Specialist | · | senior | 13-1151 | Training and Development Specialists | Business Operations Specialists |
| Lead Compliance Officer | Compliance Officer | · | senior | 13-1041 | Compliance Officers | Business Operations Specialists |
| Lead Wealth Underwriter | Underwriter | · | senior | 13-2053 | Insurance Underwriters | Financial Specialists |
| Nuclear Maintenance Technician I or Nuclear Maintenance Technician II | Maintenance Technician | · | staff | 49-9071 | Maintenance and Repair Workers, General | Other Installation, Maintenance, and Repair Occupations |
| Payroll Analyst II | Payroll Analyst | · | staff | 43-3051 | Payroll and Timekeeping Clerks | Financial Clerks |
| SVP & Chief Technology Officer | Chief Technology Officer | · | manager | 11-1011 | Chief Executives | Top Executives |
| Surgical Tech Senior | Surgical Tech | · | senior | 29-2055 | Surgical Technologists | Health Technologists and Technicians |
| Talent Acquisition & Data Manager | Talent Acquisition Specialist | · | manager | 13-1071 | Human Resources Specialists | Business Operations Specialists |
A batch of messy titles runs through ten stages. Each resolves what it can and passes the rest on. The bar fills as more of the batch is classified, reaching 99% before the last 1% goes to review.
Measured on a held-out set of several hundred thousand LinkedIn job postings and roughly two dozen large employers.
Tools used
Final state
The resolver above matches against a small synthetic sample. In production the same input runs the three model layers with the ten-stage cascade in front, over employer HRIS panels and public postings, with inference kept under tenant isolation. The evaluation numbers are from real held-out runs. Every code assigned to a title is traceable to the stage that produced it, and titles with no confident match are sent to review.