AiDash
Staff MLOps Engineer
$230K–$270K
Palo Alto, California, United States · Staff · Full-time · Posted Oct 9, 2026
- Experience
- 7–10+ years in software/ML engineering, including 3+ years specifically in MLOps or ML infrastructure.
About the job
Build and lead the technical foundation for AiDash’s model inference infrastructure, making ML model deployment scalable, reliable, and cost-efficient.
What you'll do
- Own end-to-end ML model deployment pipelines and establish CI/CD practices for testing, versioning, staged rollout, and rollback.
- Design and operate scalable inference infrastructure, managing performance, cost, monitoring, failover, and disaster recovery.
- Set MLOps technical direction and collaborate with Data Science and Web Application teams to bring models into production.
What they ask for
- 7–10+ years in software/ML engineering, including 3+ years focused on MLOps or ML infrastructure.
- Production experience deploying and serving models with AWS SageMaker or an equivalent managed ML platform.
- Track record designing production-scale systems for autoscaling, cost optimization, and resilience.
- Expertise in Docker, Kubernetes, and ML CI/CD, including model versioning, automated testing, and rollout.
Nice to have
- Experience with high-volume imagery, video, 3D, multimodal, or other unstructured data pipelines.
- Experience building MLOps from scratch, model monitoring or drift detection, GPU cost optimization, or work in regulated/enterprise B2B domains.
Pay
$230,000 to $270,000 USD annual total pay (base salary + bonus based on performance)
Tools
AWS SageMaker, Docker, Kubernetes, CPU, GPU, Inferentia, Trainium
AI focus
Operationalize AI model inference at scale, including model deployment, serving, monitoring, and cost optimization.
Model-written summary · the original posting is authoritative