Guide and expand a team of AI inference engineers dedicated to developing and scaling infrastructure for AI-powered products and APIs
Define the technical roadmap for inference systems, making critical decisions on batching, throughput, latency, and GPU efficiency
Design and scale reliable, efficient, and observable inference infrastructure while leading incident resolution efforts
Identify and resolve performance bottlenecks across the full inference stack through rigorous benchmarking
Collaborate with machine learning research teams on model optimization, quantization techniques, and deployment strategies
Build and maintain APIs for AI inference used by internal teams and external customers
Recruit, mentor, and grow engineering talent while establishing strong team processes, coding standards, and operational rigor
Coordinate closely with GenAI Platform, Data, and Product teams to deliver projects that improve healthcare outcomes for clinicians and patients

Competitive compensation and equity grants for full time employees

Hybrid — San Francisco, New York, Pittsburgh

14 paid holidays and flexible PTO for salaried employees; accrued time off for hourly workers
Comprehensive medical, dental, and vision insurance for full-time employees and their dependents
Monthly HSA contributions for employees enrolled in a High Deductible Health Plan
Generous paid leave for new parents
Financial and logistical support for family-forming efforts
401(k) plan with company matching contributions
Tax-free allowance for personal device use
Access to pre-tax benefits including Flexible Spending Accounts and commuter programs
Monthly stipend for fitness, professional growth, coworking spaces, and lifestyle expenses
Therapy and coaching services to support mental well-being
Paid sabbatical after five years of employment
Competitive salary and equity packages for full-time roles
Equal opportunity employment practices with no discrimination based on race, color, religion, sex, sexual orientation, gender identity, national origin, veteran status, or disability
Provision of reasonable accommodations during the hiring process
No requests for financial information, payments, or personal identifiers such as bank accounts or Social Security numbers during recruitment
All official recruiting communications will originate from an @abridge.com email address

Abridge is hiring an Engineering Manager, Model Inference