Engineering Manager, Model Routing & Inference

Cursor3 days ago

Location

San Francisco

Type

Full Time

Salary

USD 250,000 – 350,000

Level

Manager

Role

Engineering Manager

Posted

Apr 7, 2026

Full TimeManager

The role

Summary

Cursor is seeking an experienced Engineering Manager to lead the Model Routing & Inference team, responsible for developing and optimizing the AI inference platform that powers the company's coding automation tool. The ideal candidate will build high-performance, scalable infrastructure for AI model routing and management, balancing technical complexity with business objectives.

What you'll do

Inference Platform Leadership: Lead the Model Routing & Inference team, owning the entire inference path that powers AI interactions in the product

Technical Architecture: Design and evolve the inference gateway, creating a unified abstraction layer for multiple AI model providers

System Optimization: Manage GPU cluster utilization, capacity planning, and develop dynamic model selection systems based on cost, latency, and quality

Traffic Management: Implement routing backpressure and admission control to ensure system reliability during traffic spikes

Team Development: Recruit, hire, and mentor top inference and systems engineering talent, providing coaching and high-leverage project opportunities

What we look for

Technical

Distributed SystemsExtensive experience building high-throughput, low-latency distributed systems

Model ServingProficiency with model serving frameworks like vLLM, TensorRT-LLM, or TGI

Load BalancingAdvanced knowledge of load balancing and multi-provider architectural design

Education

Computer ScienceBachelor's or Master's degree in Computer Science, Software Engineering, or related technical field

Experience

Engineering ManagementProven track record of leading engineering teams in high-performance computing environments

Scale SystemsExperience managing systems handling millions of daily requests

Skills

Required skills

Distributed Systems ArchitectureDeep understanding of designing scalable, resilient infrastructure

Performance OptimizationAbility to analyze and optimize system performance at scale

Strategic Decision MakingExpertise in making nuanced technical decisions balancing multiple competing priorities

Nice to have

AI/ML InfrastructureExperience with AI model routing and large-scale inference platforms

Cloud Provider ManagementFamiliarity with multi-cloud and hybrid infrastructure strategies

Compensation & benefits

Salary

USD 250,000 – 350,000 (annual)

Benefits

Competitive Compensation

Highly competitive salary package for top engineering talent

Innovative Work Environment

Opportunity to work on cutting-edge AI and coding automation technologies

Professional Growth

Flat organizational structure with opportunities for significant impact and learning

Interview process

1
Initial Screening — Phone or video call with recruiting team to assess background and initial fit
2
Technical Interview — Deep-dive technical discussion focusing on distributed systems, AI infrastructure, and engineering management experience
3
Systems Design Challenge — Architectural design challenge related to inference platform routing and optimization
4
Leadership and Team Dynamics Interview — Assessment of leadership style, team development approach, and strategic thinking
5
Final Executive Interview — Discussion with senior leadership to align on vision and cultural fit