Machine Learning Engineer

We are building Q an advanced next-generation platform where the entire experience is driven by adaptive, learning-based intelligence rather than fixed or static rules

This role is not about tuning existing models.

It is about designing and building the central intelligence of the product from zero:

• A recommendation engine that competes with Amazon level systems

• A search engine that understands intent, not keywords

• A fully adaptive personalized experience

• A behavioral intelligence layer that drives real business impact

If you want a role where your work becomes the backbone of the product, this is it.

What You Will Build and Own

This is an end to end engineering role.

You will take problems from concept، design، modeling، deployment، iteration.

1) Advanced Recommendation Systems

You will design systems such as:

• Behavioral recommenders

• Collaborative filtering (user item, item item)

• Graph-based recommenders

• Session-based and sequence models

• Embedding driven ranking models

2) Intelligent Search

You will build search that truly understands users:

• Learning-to-rank models

• Semantic retrieval

• Query understanding & rewriting

• Spelling/intent correction

• Vector search and embedding pipelines

3) Full Personalization Engine

You will own:

• User segmentation & clustering

• Personalized homepages

• Dynamic product surfacing

• Behavior-driven recommendations and offers

4) Experimentation Framework

You will:

• Define A/B test structures

• Establish metrics that matter

• Analyze experiments accurately

• Drive product decisions based on evidence

5) Data Foundation for ML

You will design:

• Event tracking frameworks

• Feature stores

• Batch + streaming data pipelines

• Tight integration with backend microservices

6) Production ML Deployment

You will ship:

• Reliable, scalable ML services

• Low-latency inference pipelines

• Monitored, versioned, continuously improving models

Who You Are (The Exact Profile)

1) You have real, hands-on experience building recommendation systems from zero

Not just using libraries or pre-built models.

You have actually designed and implemented recommendation engines end-to-end, including data pipelines, candidate generation, ranking, personalization, and evaluation ,and you understand the underlying math, signals, and behavioral patterns that drive real-world recommendation quality.

2) You understand algorithms deeply

Not just frameworks.

You can explain why a model works, not just how to run it.

3) You’ve built real production systems

Even if partially.

You know the difference between academic ML and commercial ML.

4) You take ownership without waiting for direction

You design, build, and lead your area end-to-end.

5) You think in terms of business impact

You optimize for relevance, revenue, retention not just accuracy metrics.

6) You don’t accept shallow fixes

You prefer fundamental, scalable solutions that materially improve the user experience.

Required Technical Skills

• Strong Python engineering skills

• Strong ML fundamentals

• Hands-on experience in recommender systems or search

• TensorFlow or PyTorch

• Experience with embeddings and vector search (FAISS, Weaviate, Pinecone, etc.)

• Strong SQL and data manipulation

• Experience building data pipelines

• Experience shipping ML to production environments

Candidates with 3–10 years of experience are welcome if they meet the required skill level.

What You’ll Get at Q

• Full ownership no layers of bureaucracy

• Ability to build foundational systems from scratch

• A product where ML is central, not a side feature

• A fast decision-making environment

• Clear impact on thousands of users (and soon millions)