3 months ago
Redwood City, CA, USASenior
Responsibilities
- Design, build, and maintain cloud architecture, model-serving infrastructure, and ML pipelines.
- Profile and optimize database queries, APIs, ML inference, GPU utilization, memory usage, and compute costs.
- Build auto-scaling, load-balancing, caching, connection-pooling, redundancy, and disaster-recovery systems.
- Develop model deployment pipelines, versioning, A/B testing, rollout, monitoring, drift detection, retraining, experiment tracking, and model registry infrastructure.
- Implement monitoring, logging, alerting, dashboards, circuit breakers, retry logic, graceful degradation, and incident-response improvements.
- Manage infrastructure security, credentials, access control, privacy compliance, audits, and vulnerability assessments.
- Create developer tooling, document architecture and operational procedures, collaborate with product and engineering teams, and mentor team members.
Requirements
- 8+ years of experience in infrastructure engineering, DevOps, or SRE.
- Strong cloud platform expertise and experience building and maintaining deployment pipelines.
- Experience with PostgreSQL, Redis, or other production databases.
- Experience with APM tools, metrics, logging, and alerting.
- Familiarity with vector databases, model-serving frameworks, and cross-system observability and traceability.
- Experience managing and optimizing GPU workloads, real-time low-latency inference infrastructure, and LLM deployment.
- Track record of achieving 10x performance improvements and supporting A/B deployment strategies.
- Ability to debug distributed systems, optimize latency and throughput, automate repetitive work, apply security best practices, communicate clearly, collaborate cross-functionally, and operate effectively in a changing startup environment.
- Strong ownership, delegation, mentoring, technical strategy, and architectural decision-making skills.
Benefits
- Medical, dental, and vision coverage begins on day one.
- Unlimited PTO with a requirement to take at least one continuous week per year.
- 401(k) with company match.
- Remote-flexible work arrangement with office attendance when needed.
- Parental leave benefits.
- Ongoing industry and professional development training.
Tech Stack
PostgreSQLRedis
Categories
