about 3 hours ago
Responsibilities
- Lead architecture and performance initiatives for the Kubernetes-native inference platform.
- Define and implement complex design initiatives across multiple teams.
- Optimize inference performance through advanced techniques like speculative decoding.
- Establish performance benchmarking frameworks and metrics-driven engineering practices.
- Mentor senior and mid-level engineers to elevate technical standards.
Requirements
- 8–12+ years of experience in large-scale distributed systems or cloud platforms.
- Strong coding skills in Go, Python, or C++.
- Deep expertise in Kubernetes at production scale.
- Hands-on experience with inference systems and performance optimization.
- Bachelor’s degree in Computer Science, Engineering, or a related field.
Benefits
- 100% paid medical, dental, and vision insurance.
- Company-paid life insurance and disability insurance.
- Tuition reimbursement and employee stock purchase program.
- Flexible PTO and paid parental leave.
- Catered lunch each day and a casual work environment.