Senior ML Engineer Recommendation Systems
@ Launch Potato

Hybrid
$170,000
Hybrid
Full Time
Posted 23 days ago

Your Application Journey

Personalized Resume
Apply
Email Hiring Manager
Interview

Email Hiring Manager

XXXXXXXX XXXXXXXXXXXXX XXXXXXXXXX***** @launchpotato.com
Recommended after applying

Job Details

About Launch Potato

Launch Potato is a profitable digital media company reaching over 30M+ monthly visitors with brands like FinanceBuzz, All About Cookies, and OnlyInYourState. Headquartered in South Florida with a remote-first team spanning 15 countries, the company drives success through speed, ownership, and measurable impact.

Why Join Us?

At Launch Potato, you will accelerate your career by owning outcomes and driving impact with a global high-performance team. The role centers on converting audience attention into action through data, machine learning, and continuous optimization.

Your Role as Senior ML Engineer Recommendation Systems

You will build the personalization engine powering recommendations across millions of user journeys. This includes designing, deploying, and scaling ML systems that serve over 100M predictions daily, directly impacting engagement, retention, and revenue.

Key Responsibilities

  • Build and deploy ML models serving 100M+ predictions per day.
  • Enhance data pipelines using tools like Spark, Beam, and Dask.
  • Design ranking algorithms balancing relevance, diversity, and revenue.
  • Deliver real-time personalization with latency under 50ms.
  • Run statistically rigorous A/B tests to gauge business impact.
  • Optimize latency, throughput, and cost efficiency in production systems.
  • Collaborate with product, engineering, and analytics teams.
  • Implement monitoring systems and maintain model reliability post-deployment.

Required Experience & Skills

  • 5+ years building and scaling production ML systems.
  • Experience deploying ML systems serving 100M+ predictions daily.
  • Expertise in ranking algorithms (collaborative filtering, learning-to-rank, deep learning).
  • Proficiency in Python and ML frameworks like TensorFlow or PyTorch.
  • Skilled with SQL, data warehouses (Snowflake, BigQuery, Redshift), and data lakes.
  • Experience with distributed computing frameworks such as Spark or Ray.
  • Familiarity with LLM/AI Agent frameworks and A/B testing methodologies.

Competencies

  • Technical Mastery in ML architecture and tradeoffs.
  • Ability to set up experimentation infrastructure (MLflow, W&B).
  • Impact-driven design moving key business KPIs.
  • Collaborative mindset working with cross-functional teams.
  • Strong analytical thinking and rigorous testing methods.
  • Ownership mentality with commitment to continuous model improvement.
  • Fast execution of production-grade systems.
  • Curiosity and innovation in applying the latest ML advances.

Total Compensation

The base salary is set according to market rates and performance levels, complemented by profit-sharing bonuses and competitive benefits. Increases are based on company and personal performance.

Commitment to Diversity

Launch Potato is an Equal Employment Opportunity company committed to diversity, equity, and inclusion.

Key skills/competency

Machine Learning, Personalization, Ranking Algorithms, Python, TensorFlow, PyTorch, SQL, Data Warehousing, Distributed Computing, A/B Testing

How to Get Hired at Launch Potato

🎯 Tips for Getting Hired

  • Customize your resume: Highlight large-scale ML system experiences.
  • Research Launch Potato: Understand their digital media and ML initiatives.
  • Prepare for technical screening: Review ranking algorithms and ML deployments.
  • Showcase your impact: Emphasize measurable business outcomes in your projects.

📝 Interview Preparation Advice

Technical Preparation

Review large-scale ML system architecture.
Practice ranking algorithm implementation exercises.
Brush up on distributed computing frameworks.
Test coding in Python and ML framework libraries.

Behavioral Questions

Discuss a challenging project you led.
Explain your collaboration with cross-functional teams.
Describe a time you optimized system performance.
Share how you handle feedback and failures.

Frequently Asked Questions