Algorithm Evaluation Manager

We are looking for an experienced and highly motivated Engineering Manager to lead a dynamic team focused on machine learning algorithms or Large Language Model (LM) evaluation. In this role, you will guide a team responsible for the critical data and evaluation pipelines that ensure our models are accurate, robust, and performant. The ideal candidate will bring a strong mix of technical leadership, expertise in data curation and annotation processes, and deep analytical skills. You will collaborate closely with cross-functional research and engineering teams, requiring exceptional communication and strategic thinking. As the Engineering Manager for this team, you will be at the forefront of our AI/ML development lifecycle. Your day-to-day responsibilities will include:

• Team Leadership: Lead, mentor, and grow a team of engineers and data specialists. Foster a culture of innovation, rigorous analysis, and continuous learning.
• Evaluation Strategy: Define and execute the evaluation strategy for both CV and LM models. Build robust, scalable evaluation pipelines that accurately reflect real-world performance.
• Data Pipeline Management: Oversee the end-to-end data lifecycle. This includes establishing data curation guidelines, managing data quality, and optimizing large-scale annotation workflows with external vendors or internal teams.
• Analytical Deep Dives: Guide the team in performing rigorous data analysis to troubleshoot model regressions, uncover data quality issues, and identify opportunities for algorithmic improvements.
• Strategic Alignment: Act as the primary point of contact for your team, communicating progress, bottlenecks, and strategic data needs to leadership and partner teams.Education & Experience: BS and a minimum of 10 years relevant industry experience Management Experience: 2+ years of direct people management experience, with a track record of hiring, mentoring, and leading high-performing technical teams. Domain Expertise: Proven experience in model evaluation, benchmarking, and A/B testing methodologies for machine learning models (Computer Vision or Foundation Models). Inference Infrastructure: Familiarity with the design and architecture of machine learning inference pipelines and underlying infrastructure. Data & Annotation: Hands-on experience designing and managing data curation strategies and human-in-the-loop annotation processes. Data Analysis: Strong analytical skills with the ability to dive deep into datasets to identify trends, biases, and areas for model improvement. Communication: Excellent verbal and written communication skills, with the ability to translate complex technical concepts to both technical and non-technical stakeholders.Advanced Degree: PhD in Computer Science, Machine Learning, or a related field. Deep Domain Knowledge: Expertise in both Computer Vision (CV) algorithms and Large Language Model (LM) evaluation methodologies (e.g., RLHF, prompt evaluation). Scale & Operations: Experience scaling large data operations, managing complex annotation workflows, and working directly with external data vendors. Technical Stack: Familiarity with Python, SQL, and ML frameworks (e.g., PyTorch) to effectively review technical work and guide engineering decisions. Cross-Functional Leadership: Demonstrated ability to drive strategic alignment across downstream product teams, ML researchers, and platform engineers in a highly matrixed environment.