ML/NLP engineer

We’re looking for an experienced ML/NLP engineer to analyze ~700k job records and identify niches and sub-niches.

Scope: Generate embeddings from job titles/descriptions Cluster jobs into meaningful groups (niches) Create sub-clusters (sub-niches) Auto-label clusters using LLMs Provide clean structured output

Requirements: Experience with embeddings (OpenAI or sentence-transformers) Clustering (HDBSCAN, KMeans) Python (pandas, scikit-learn) Experience with large datasets

Nice to have: FAISS or vector DB experience Previous work with marketplace/job data

Deliverables: Script/pipeline Clustered dataset List of niches with labels

To apply: Please share a similar project you’ve done and briefly explain your approach.