Machine Learning Engineer - Recall Team: Search Quality

About Us

Our team focuses on improving the search system’s quality by increasing the recall and relevancy of the retrieved results. We consistently deliver measurable KPI improvements, resulting in better search experiences and greater transparency in our algorithms for customers.

We are looking for a Machine Learning Engineer with experience in building and optimizing search or recommendation systems.

In this role, you’ll address practical challenges in building and optimizing models that improve search quality. Your work will involve fine-tuning large language models, integrating advanced vector search techniques, and using real-time relevance signals to align results with user intent.

The ideal candidate has a strong background in machine learning and information retrieval, along with experience delivering scalable, production-ready solutions. You’ll collaborate across the stack - from model development to deployment - to drive measurable improvements in search performance and user satisfaction, directly contributing to a superior product discovery experience.

Challenges you will tackle

• Build and deploy robust ML systems for search, including vector search, results filtering, computer-vision models, etc.
• Tune large language models (LLMs) to provide expert-level decisions on item relevance, and work on integrating these signals into real-time models.
• Design metrics to evaluate the relevance and performance of search results, ensuring they align with business goals and user expectations.
• Collaborate with technical and non-technical partners to develop explanation tools that clearly communicate the impact of our algorithms to stakeholders.
• Own the full development lifecycle: design solutions, develop and deliver them to production, while ensuring our systems remain stable, performant and scalable.

Hard skills:

• You are proficient in NLP on a high level, and have practical experience with modern architectures.
• You excel at Python, at least one ML/DL framework (we're using torch), have proficiency with any variant of SQL, and feel comfortable with the big data stack like Spark, Presto/Athena & Hive.
• You have delivered production ML systems and conducted A/B tests to validate their value.
• You have experience with data pipeline orchestration tools (Airflow) to manage and automate ML workflows.
• You are an excellent communicator with the ability to translate intuition into data-driven hypotheses that result in engineering solutions that bring significant business value.

Soft skills:

• Excellent English communication skills.
• Passion for helping others grow and succeed as developers.
• Data-driven mindset with a passion for experimenting and using customer feedback to drive decision-making.
• Strong strategic planning and prioritization skills.
• Continuous learning and tracking of recent advancements in the field of AI and ML.