Staff ML/LLM Ops Engineer

Responsibilities

• Own the end-to-end model lifecycle including standardized packaging, CI/CD, serving layers, and monitoring
• Implement LLMOps for LLM, VLM, and agentic workloads, including prompt versioning, generative evaluation, and guardrails
• Develop self-serve CI/CD paths to encode security, observability, and operational guardrails
• Define and own the API contract boundary between the model platform and application backend
• Provide technical mentorship and set engineering standards for productionization

Requirements

• 8+ years of engineering experience with deep ML-infrastructure or MLOps expertise
• Hands-on experience operating LLM or VLM workloads in production
• Experience designing self-serve ML deployment systems (model registry, CI/CD, drift monitoring)
• Strong systems and API design judgment
• Proven track record of technical leadership
• Bachelor's or Master's degree in Computer Science, Engineering, or a related field

Preferred Qualifications

• Experience with computer vision or video model inference at scale
• Proficiency with cloud-native infrastructure like Kubernetes or Argo
• Experience building an ML platform from the ground up
• Experience deploying AI models to edge environments (e.g., NVIDIA Jetson)
• Familiarity with LangGraph, MCP frameworks, vector databases, and inference platforms

Benefits

• Comprehensive health, dental, and vision coverage
• 401k with up to 4% match
• Flexible PTO
• Employee equity program
• Performance-based bonus structure

About the Company

LVT is redefining how businesses operate in the physical world by delivering AI-driven, actionable intelligence for smarter and safer sites. Recognized as one of the Financial Times’ Fastest Growing Companies 2025, LVT builds next-generation solutions ranging from solar-powered physical units to powerful Agentic AI platforms.