MLOps Engineer

Job summary

The Senior MLOps / LLMOps Engineer leads deployment, orchestration, monitoring, and reliability for production LLM applications and agentic AI workflows. The role operates secure AI services and data pipelines in large-scale Kubernetes environments, builds CI/CD, observability, and evaluation systems, and optimizes inference performance and infrastructure costs using technologies such as Python, Prometheus, OpenTelemetry, and vector databases.

Benefits

Qualifications

• At least 3 years of experience in MLOps, LLMOps, platform engineering, AI infrastructure, or SRE focused on machine learning workloads.
• Experience deploying complex containerized applications at scale on Kubernetes, including EKS, GKE, AKS, or bare metal.
• Strong Python skills for automation, debugging, tooling, and integrations.
• Experience with monitoring, logging, LLM tracing, and evaluation platforms.
• Familiarity with CI/CD pipelines and Infrastructure as Code tools.
• Operational understanding of agentic architectures, prompt chaining, function calling, tool execution, and non-deterministic applications.
• Experience operating RAG pipelines and production vector databases.
• Exposure to agent development and orchestration frameworks.
• Experience with high-performance LLM serving engines and frameworks.
• Understanding of AI security practices and rate limiting or cost controls.

Responsibilities

• Deploy and manage LLM services, agentic applications, and AI workloads in high-throughput Kubernetes clusters.
• Automate containerized deployments, inference endpoints, and blue/green or canary releases through CI/CD pipelines.
• Operate agentic workflows, including multi-step tool execution, state management, and multi-agent coordination.
• Triage and resolve issues across AI application logic, orchestration frameworks, external APIs, and cloud infrastructure.
• Build monitoring and evaluation frameworks for output accuracy, drift, latency, cost, and hallucinations.
• Implement trace-level observability for prompts, completions, tool calls, and agent steps.
• Monitor and optimize AI data pipelines, feature stores, vector indexing, and embedding updates.
• Optimize GPU and CPU allocation, memory use, autoscaling, infrastructure costs, time-to-first-token, and throughput.

Skills

Languages

Industry

Relocation