Junior AI Query Spell Correction and Normalization Developer

Quelion Cloud

Remote · $60k – $80k / year · Contract · Posted 4 months ago

This role is no longer accepting applications

Don't miss the next role like this

Create a free profile with your skills. We match you to new AI roles as they open, and companies hiring can contact you directly.

Create free profile, 2 minutes

Similar open roles you can apply to now:

See all open AI jobs

This role is no longer accepting applications

Don't miss the next role like this

Create a free profile with your skills. We match you to new AI roles as they open, and companies hiring can contact you directly.

Create free profile, 2 minutes

Similar open roles you can apply to now:

See all open AI jobs

About the role

Search queries arrive misspelled, abbreviated, using inconsistent terminology, and mixing technical and colloquial names for the same concept. A user who types 'machien lerning jubs' is looking for machine learning jobs. A user who types 'ML eng' and a user who types 'machine learning engineer' have the same intent. Query normalization — correcting spelling errors, expanding abbreviations, and standardizing terminology — is the preprocessing layer that makes downstream search quality possible. This is a 9-month contract. We run search for 55 enterprise clients, and query quality varies enormously by client domain: technical queries in developer tools platforms have different misspelling patterns than natural language queries in consumer retail search. A single spell correction model trained on generic text doesn't serve both well. As a junior developer, you'll build the domain-adaptive query normalization pipeline: spell correction model serving, abbreviation expansion dictionaries, query term standardization, and the A/B testing infrastructure that measures whether normalization changes improve downstream search quality. Senior NLP engineers design the models; you build the serving and evaluation infrastructure.

Fully remote.

Responsibilities

Build spell correction model serving infrastructure for domain-adaptive query correction
Implement abbreviation expansion dictionary management for client-specific terminology
Develop query term standardization mapping colloquial and technical synonyms to canonical search terms
Create A/B testing infrastructure measuring the impact of normalization changes on downstream search metrics
Build normalization logging for query correction audit trails and model improvement feedback
Maintain normalization pipeline as new client domains and terminology corpora are added

Requirements

1+ year of Python and SQL development experience
Basic familiarity with NLP libraries or text processing
Interest in search technology, NLP, or developer infrastructure
Attention to correctness in text transformation and domain-specific normalization
Reliable async communication for a contract engagement