This is a Fully Remote Job
About Our Client:
Positron operates within the technology sector, focusing on systems that provision, deploy, observe, upgrade, and reliably operate software platforms in production environments. The organization addresses the challenges of managing and scaling large fleets of systems by developing robust software and operating practices that enhance production reliability and operational efficiency. With a rapidly expanding fleet, the team supports complex orchestration and production platform needs, collaborating closely with hardware, compiler, runtime, and customer-facing partners to improve performance and scalability.
About the Opportunity:
The ENGINEERING MANAGER, SERVING/API role leads a team responsible for the software that processes customer API requests and generates accurate responses through model outputs. This position involves technical leadership and product accountability, guiding the development and operation of the serving layer, including API compatibility, tokenization, tool integration, reasoning, and support for new model modalities. The role is critical in ensuring reliable and efficient API serving, enabling scalability and integration with evolving model capabilities, and collaborating cross-functionally to deliver production-ready solutions.
Responsibilities:
- Lead and grow a team spanning API serving, tokenization, structured generation, and model integration.
- Develop and maintain the technical and organizational roadmap for the serving layer.
- Ensure OpenAI-compatible API behavior, streaming, usage accounting, and robust error handling.
- Manage reasoning-model support, including parsing, effort controls, token limits, and budgeting.
- Collaborate on speculative decoding strategies and integration with draft models.
- Plan and implement support for vision-language models and interoperability frameworks.
- Optimize serving-layer performance to minimize latency.
- Maintain hardware topology independence for the API layer.
- Define ownership and policies for host-level load balancing in coordination with platform teams.
- Implement release gates and testing suites to ensure quality and confidence in new features.
- Convert customer and business priorities into structured engineering activities.
- Hire, develop leaders, and establish scalable ownership boundaries within the team.
Requirements:
- Proven experience in technical leadership of engineering teams focused on API serving or related domains.
- Strong background in systems architecture, deployment lifecycle, and production reliability.
- Expertise in API design, tokenization, and structured output handling.
- Familiarity with model serving technologies, including speculative decoding and reasoning mechanisms.
- Ability to collaborate across diverse technical teams and manage operational accountability.
- Skilled in planning roadmaps and driving product and technical outcomes.
Pay Range and Compensation Package:
- The pay range and compensation package for this role will be determined based on the candidate's experience, skills, and other relevant factors.
Equal Opportunity Statement: Our client is an equal opportunity employer. They celebrate diversity and are committed to creating an inclusive environment for all employees. All qualified applicants will receive consideration for employment without regard to race, color, religion, gender, gender identity or expression, sexual orientation, or national origin.
Note:
TalentHop is a recruitment partner of this role. Please note that all employment decisions, including candidate assessment, interviews, hiring, compensation, and employment terms, are made exclusively by the hiring employer.