Lead Machine Learning Engineer - Search & Recommendations
Lead Machine Learning Engineer to build personalized memory systems for Search & Recommendations, improving user intent understanding and engagement.
Lead Machine Learning Engineer – Search and Recommendations
We’re looking for a Lead Machine Learning Engineer to build personalized memory systems for Search and Recommendations, enabling models to better understand user intent, preferences, and evolving needs across interactions.
This role sits at the intersection of memory modeling, retrieval, ranking, and personalization, with a primary focus on learning and applying personalized memory representations rather than building general-purpose memory infrastructure. You will design how memory signals are encoded, updated, decayed, and surfaced to influence candidate retrieval, ranking, and personalization decisions across the marketplace.
As a Lead-level individual contributor, you will own complex technical initiatives, work closely with engineering, research, product, and data partners, and translate personalized memory concepts into robust, measurable, production-ready machine learning systems that improve relevance, engagement, and hiring outcomes.
Responsibilities
Design and build personalized memory systems for Search and Recommendations that improve understanding of user intent, preferences, and behavioral evolution.
Develop user-, session-, and interaction-level memory representations that directly inform candidate retrieval, ranking, and personalization decisions.
Integrate memory-driven signals into retrieval and ranking pipelines to improve relevance, engagement, and downstream hiring outcomes.
Model temporal dynamics of user behavior, including recency, frequency, decay, and preference drift, translating them into stable, high-impact personalization features.
Train and evaluate memory-aware ranking and personalization models using offline relevance metrics and online experimentation frameworks.
Partner with conversational and LLM-assisted search teams to support context-aware query understanding while maintaining focus on search relevance and ranking quality.
Productionize memory-driven ML systems with an emphasis on latency, scalability, observability, and experimentation rigor.
Provide technical leadership through design reviews, mentorship, and shared best practices for building scalable personalization systems.
What it takes to catch our eye
Demonstrated experience building and deploying search or recommendation systems in production with measurable impact on relevance, engagement, or conversion metrics.
Strong foundation in retrieval and ranking systems, including candidate generation, re-ranking, and offline and online evaluation techniques.
Practical experience modeling personalization and behavioral memory, including user intent, preferences, temporal dynamics, and signal tradeoffs.
Solid machine learning engineering skills across the full lifecycle, including pipelines, experimentation, deployment, and inference at scale.
An adaptive approach to integrating AI tools into modeling and engineering workflows to accelerate experimentation, improve quality, and support team learning.
Comfort operating in ambiguity, with the ability to define open-ended problems, design experiments, and iterate based on data.
Bonus experience contributing to applied research, publications, or experimentation in search, recommendation, or applied machine learning.
This position will initially be employed through a partner to ensure a seamless hiring process while we establish the hub. Once the hub is established, there may be opportunities to transition to employment with Upwork depending on business needs and other requirements. While employed by the partner, you’ll work as part of Upwork’s team, with access to our resources, culture, and growth opportunities.
To learn more about how Upwork processes and protects your personal information as part of the application process, please review our Global Job Applicant Privacy Notice