Sequen
Staff, MLOps Engineer
$220K–$280K
United States · Remote · Staff · Full-time · Posted Jul 8, 2026
- Experience
- 4–8+ years in MLOps, Machine Learning Engineering, or distributed platform/infrastructure engineering.
About the job
Build and operate infrastructure for low-latency production machine-learning model serving, evaluation, deployment, and scaling.
What you'll do
- Design and maintain model deployment, distributed inference, and real-time telemetry systems.
- Build model CI/CD, evaluation, and observability pipelines; optimize serving performance and infrastructure costs.
- Work with ML researchers and backend engineers to move experimental models into production.
What they ask for
- Hands-on experience serving low-latency ML models under heavy real-time workloads.
- Production-grade proficiency with Python and PyTorch.
- Experience with a major cloud platform (AWS, GCP, or Azure), Docker, and Kubernetes.
- Experience with data pipelines, model registries, and CI/CD; understanding of ML lifecycle, event-driven patterns, and distributed systems.
Nice to have
- Production experience or hands-on familiarity with Rust.
- Exposure to serving and optimizing LLMs or large-scale generative models, such as vLLM or Triton.
Pay
$220K – $280K (base salary)
Tools
Python, PyTorch, AWS, GCP, Azure, Docker, Kubernetes, MLflow
AI focus
Infrastructure for deploying, serving, evaluating, and scaling AI ranking models in production; preferred experience includes serving and optimizing LLMs or other generative models.
Model-written summary · the original posting is authoritative