# Machine Learning Engineer (Recommender Systems)

A full-time, remote engineering role for elite ML practitioners architecting state-of-the-art recommender systems and leveraging Generative AI for Fortune 500 U.S. companies.

### **Design, Build and Deploy**

Architect and operationalize end-to-end machine learning pipelines utilizing Databricks and Spark for web-scale data processing.

Justify critical architectural decisions across complex recommendation frameworks, from Wide & Deep and Two-Tower systems to sequential GRU4Rec models, with first-principles reasoning.

Deploy high-dimensional user embeddings, hybrid search strategies, and continuous evaluation frameworks that go directly to production.

### **Operating in a High-Bar Environment**

Work among senior ML engineers who hold elite standards, no hand-holding, full end-to-end pipeline ownership expected.

Your systems reach real Fortune 500 U.S. clients, algorithmic latency, retrieval precision, and pipeline reliability are your core accountabilities.

This is production-grade machine learning, not experimental modeling, static prototypes, or basic demos.

## Architect the personalization ecosystems that power enterprise-scale product discovery.

### **Distributed Pipeline Infrastructure**

Building and managing large-scale, high-throughput feature engineering and data processing pipelines utilizing PySpark within Databricks platforms.

### **Advanced Deep Recommendation**

Networks Implementing and optimizing sophisticated architectures, including Two-Tower, Transformer-based, and deep sequential models, to capture evolving user intent at scale.

### **Discovery & Search Optimization**

Deploying high-dimensional user embeddings and hybrid search strategies to maximize retrieval precision, semantic product discovery, and user engagement across platforms.

### **Statistical Rigor & Validation**

Designing clean experimental frameworks, continuous drift monitoring, and robust A/B testing pipelines mapped directly to core enterprise business KPIs.

## Selection Process

### **Validate Your Foundation**

Submit your application. We prioritize engineers with proven production experience, deep algorithmic skills, and the domain fluency to communicate technical trade-offs clearly in English.

### **Prove Your Craft**

Complete a focused technical assessment, then demonstrate your mastery in live coding, machine learning fundamentals, and scalable system design.

### **Join the team and build the future of data and AI**

Work as a full-time Factored engineer, embedded as a strategic partner in environments where your execution directly transforms real systems and impacts global users.

## FAQs

What makes Factored different?

What kind of work will I do?

What kind of engineers succeed at Factored?

How will I grow at Factored?

What does working at Factored look like?

What benefits and support do you offer?

What is the selection process like?

## **Research \|** Our team has published at NeurIPS, ICML, NASA and more.

Architecting Trust in AI Agents

91% completion, reasoning still fails

Medical LLMs: Real-World Risks

1,298-person study reveals reliability gaps

Multilingual Data Workshop

Doubles cross-language consistency