Engineering Manager, API Serving

Job Summary

Leading a strong team in a remote, full-time capacity, the Engineering Manager, API Serving will oversee the development and operational practices for API fidelity, tokenization, and model integration, ensuring reliable production systems as the organization scales.

Key responsibilities

• Lead, coach, and grow a team of engineers focused on API serving, tokenization, and structured generation
• Establish a technical roadmap for the serving layer, ensuring API fidelity and supporting new models
• Collaborate with cross-functional teams to improve systems behind API performance and operational reliability

Required qualifications

• Demonstrated success managing engineering teams in LLM inference or model serving
• Proficiency in C++ and working knowledge of Python, with experience in performance-critical code
• Ability to translate ambiguous product demands into coherent roadmaps and measurable outcomes
• Experience in recruiting and developing engineers while maintaining high technical standards
• Hands-on leadership style with the ability to engage in architecture and code discussions