Applied ML Engineer – Semantic Ingestion & Search

Infuse; Remote; ZAR 600 000 - 800 000; Full time

Job summary

A data-driven tech company in Pretoria is seeking an applied ML engineer to manage the semantic ingestion pipeline from raw data to structured resources. The successful candidate will own the ETL process, finalize summarization techniques, and generate embeddings, employing technologies like Python, FastAPI, and Milvus. This role is crucial for enhancing the relevance and freshness of over a million resources and providing impactful insights to users.

Qualifications

• 3+ years of experience in machine learning or data engineering.
• Experience with semantic search and handling unstructured data.
• Ability to build and optimize ETL pipelines.

Responsibilities

• Own the ETL pipeline from raw PDFs to structured resources.
• Finalize summarization and classification flow using open-source models.
• Generate embeddings using sentence-transformers.

Skills

Python

PyTorch

ML pipelines

semantic search

embeddings

Docker

Tools

FastAPI

Milvus

pgvector

Airflow

GPU scheduling

Job description

A data-driven tech company in Pretoria is seeking an applied ML engineer to manage the semantic ingestion pipeline from raw data to structured resources. The successful candidate will own the ETL process, finalize summarization techniques, and generate embeddings, employing technologies like Python, FastAPI, and Milvus. This role is crucial for enhancing the relevance and freshness of over a million resources and providing impactful insights to users.