MLOps Engineer

Job summary

Seeking a MLOps Engineer to design, build, and operate high-performance inference platforms for large machine learning models in production, focusing on systems engineering for AI deployment.

Qualifications

• Six or more years of experience in distributed systems or ML platform engineering.
• Strong proficiency in Python and a systems language.
• Experience operating high-throughput, low-latency services.
• Hands-on experience with LLM inference frameworks.
• Understanding of GPU architecture and accelerator utilization.
• Familiarity with Kubernetes and modern cloud platforms.
• Experience with observability stacks.
• Grounding in performance engineering and capacity planning.
• Strong communication and incident response skills.

Responsibilities

• Design and operate model serving platforms for diverse workloads.
• Optimize inference performance with batching and request multiplexing.
• Implement multi-tenant routing and quality-of-service policies.
• Build autoscaling and capacity management systems.
• Tune GPU utilization and memory management for LLM workloads.
• Integrate model serving with API gateways and observability platforms.
• Implement caching and response reuse strategies.
• Drive end-to-end observability and error tracking.
• Develop deployment workflows including canary releases.
• Operate incident response for high-availability AI services.
• Collaborate with ML and product teams for model releases.
• Implement security controls at the serving layer.
• Document operational procedures and tuning guidance.
• Stay current with AI serving research.

Skills

Degrees

Relocation