Semantic Backend Engineer (Contract, Remote)

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

Job summary

A leading technology company in Northern Cape, South Africa, is seeking an applied ML engineer to take ownership of the semantic ingestion pipeline. The role involves developing and optimizing the ETL process, utilizing advanced machine learning models, and ensuring data relevance and freshness. Ideal candidates will have experience in building ML pipelines that benefit real users, along with skills in Python and semantic search technologies.

Qualifications

• Experience in building ML pipelines that reach real users.
• Experience with semantic search and handling unstructured data.
• Familiarity with fresh content identification and indexing.

Responsibilities

• Own the ETL pipeline from raw PDFs to structured resources.
• Implement logic to generate embeddings and perform semantic searches.
• Collaborate with the Tech Lead on UX integration.

Skills

Python

PyTorch

Semantic search

Large-scale tagging

Embedding techniques

Tools

FastAPI

Docker

Milvus

AWS Lambda

Job description

INFUSE is committed to complying with applicable data privacy and security laws and regulations.

For more information, please see our Privacy Policy.

Overview

INKHUB is ingesting 10 million raw PDFs to build the Internet's richest catalog of marketing-grade B2B content — tagged, summarized, and searchable by topic, company, or intent.

We're looking for an applied ML engineer to own the semantic ingestion pipeline, from raw PDFs to tagged, summarized, and embedded assets.

What You'll Do

Own the ETL pipeline from raw PDFs (S3-ingested) to structured resources.

Finalize our summarization and classification flow using open-source models with GPT-4o fallback.

Apply filtering logic (=3 years old, = pages, etc.) to enforce resource quality.

Map each asset to the specific topic taxonomy (10+ per topic across ~9, topics).

Generate dense embeddings using sentence-transformers.

Load and query embeddings using Milvus or pgvector.

Implement "freshness" logic to identify and index only new or updated content based on file diffing, crawl timestamp, or document hash.

Build a QA / eval harness : format compliance, , drift monitoring.

Expose / v1 / semantic-search via FastAPI, with filtering and rank fusion.

Collaborate closely with our Tech Lead on UX integration and snippet generation.

Your Toolbox

Python, PyTorch, sentence-transformers, OpenAI APIs, or similar pretrained LLMs.

FastAPI, Milvus or pgvector, PyPDF / Tika, Airflow or Lambda for orchestration.

Docker, GPU scheduling, Athena / Redshift SQL.

You Might Be a Fit If

You've built ML pipelines that touched real users, not just notebooks.

You've worked on semantic search, embeddings, or large-scale tagging.

You've wrestled with unstructured data and love turning chaos into clarity.

You like working fast, iterating with feedback, and tracking metrics that matter.

Why This Role Matters

Your models decide what gets found, how it's tagged, and which content and companies stand out.

You'll help define what "relevance" and "freshness" mean for over a million resources and 50,+ company pages and make sure INKHUB stays ahead of the curve.

Referrals increase your chances of interviewing at INFUSE by 2x.

Be among the first 25 applicants to get a fair and detailed assessment from our seasoned recruiting professionals.