ML Engineer - Recommendation Systems

Build the AI brain behind the future of newsletter reading

THAtha.org & Quokka For Good LLC

You'll be our first ML hire, owning the entire recommendation engine from scratch.

🧠 What You'll Build

AI Recommendation Engine

• Design hybrid recommendation system

  - collaborative filtering + content-based + behavioral analysis

• Build semantic embeddings

  for 50,000+ newsletters using LLMs (BERT, OpenAI)

• Implement fatigue-aware algorithms

  to prevent user burnout and over-recommendation

• Create cold-start solutions

  for new users using onboarding signals and peer behavior

• Develop continuous learning

  systems that adapt from user interactions in real-time

Data Collection & Enrichment

• Web scraping pipelines

  to collect newsletter metadata, social signals, and authority scores

• Content categorization

  using L1-L4 hierarchical taxonomy and AI-generated tags

• Publisher data enrichment

  - subscriber counts, engagement metrics, domain authority

• Automated data quality

  validation and duplicate detection systems

Backend API Development

• FastAPI/Flask APIs

  to serve recommendations to React Native mobile app

• Real-time scoring

  for personalized discovery, "You might like," and trending sections

• A/B testing infrastructure

  for algorithm experimentation and optimization

• Performance monitoring

  and recommendation analytics dashboards

🛠️ Tech Stack

ML/AI:

Vector Search:

Data Pipeline:

Backend:

Cloud:

Monitoring:

✅ What We Need (Recommendation Systems Focus)

Essential ML Experience

• 1-3 years

  building recommendation systems or similar personalization engines

• Production ML experience

  - deployed models serving real users at scale

• Recommendation algorithms

  - collaborative filtering, content-based, hybrid approaches

• NLP and embeddings

  - semantic similarity, text classification, content understanding

• Python expertise

  with ML libraries (PyTorch/TensorFlow, Scikit-learn)

• Vector databases

  and similarity search (FAISS, Pinecone, or similar)

• Data engineering

  skills for processing large datasets and building ML pipelines

Data Collection & Backend Skills

• Web scraping experience

  - extracting data from various platforms and APIs

• API development

  using FastAPI/Flask for serving ML models

• Database design

  for user behavior tracking and content metadata

• Real-time systems

  experience with low-latency recommendation serving

• A/B testing

  and experimentation frameworks for ML model optimization

Startup & Domain Experience (Preferred)

• Content/publishing platforms

  - newsletters, media, or content recommendation systems

• Cold-start problems

  - handling new users and items in recommendation systems

• Behavioral analytics

  - user engagement patterns, fatigue detection, personalization

• Early-stage startup

  experience with wearing multiple hats and fast iteration

💰 What We Offer

Compensation:

Equity:

Work Style:

🤝 You'll Work Closely With

Mobile Developer

Founders

Early Users

This is a high-impact role where your algorithms will directly influence how thousands of people discover and consume content daily.

Additional Info

• You'll be the sole ML expert - no ML team to learn from, you make all technical decisions.
• Requirements will evolve based on user feedback and business needs - flexibility required.
• You may need to handle DevOps and infrastructure for your models alongside ML development.