Senior AI Operations Engineer at Robinhood · LumiJobs

Responsibilities

Build internal tooling, automation, and self-service solutions that streamline AI operations, reduce manual intervention, and improve the developer experience.
Own complex technical troubleshooting and escalations across AI platforms, working directly with developers and internal teams to resolve issues involving LLM integrations, model behavior, APIs, and system performance.
Manage and optimize enterprise integrations with LLM providers, including Anthropic Claude and Google Gemini, focusing on performance, token utilization, reliability, and cost efficiency.
Develop and improve observability, monitoring, and deployment pipelines for AI workloads, tracking metrics such as inference latency, API costs, token usage, and error rates.
Support and optimize agentic workflows, orchestration layers, vector databases, and retrieval-augmented generation (RAG) systems to improve reliability and scalability.
Partner with Product, Software Engineering, Business Systems, and AI Strategy teams to identify recurring issues, incorporate user feedback, and drive long-term improvements to enterprise AI capabilities.
5+ years of experience in IT Operations, Site Reliability Engineering, or AI infrastructure and support, with a track record of operating complex production systems.
Hands-on experience with enterprise AI platforms and LLM integrations, particularly Anthropic Claude and Google Gemini, including API integrations, prompt operations, and token management.
Strong Linux administration skills and proficiency in scripting and automation using Python, Bash, or similar languages.
Experience with infrastructure provisioning, configuration management, and orchestration tools such as Terraform, Ansible, Chef, or Kubernetes.
Strong understanding of production infrastructure, system reliability, monitoring, and troubleshooting across cloud or on-premises environments.
Ability to independently investigate ambiguous technical problems, identify root causes, and develop scalable solutions that prevent recurring issues.

Senior AI Operations Engineer

Responsibilities

Benefits

Company

Robinhood

More roles at Robinhood