Support Engineer AI Software & Tools

Overview

We are seeking a highly technical and versatile Support Engineer AI Software & Tools to join our team. This role will focus on rapid response and resolution of issues in our cutting-edge AI software and tools. The ideal candidate possesses a strong understanding of AI and LLM concepts with a proven track record in technical support engineering and troubleshooting. This candidate will have an extraordinary opportunity to help drive platform adoption and influence customer trust on our AI products which are rapidly evolving in a complex technical landscape.

Responsibilities

• First line of response for customer and application issues for our AI platforms.
• Instrumenting and maintaining effective monitoring and alerting for our AI services including LLM and agent monitoring frameworks.
• Implementing adequate Incident Management and Postmortem processes.
• Resolving deep technical issues end to end utilizing AI and Technical subject matter expertise.
• Effectively escalate issues to engineering teams when appropriate.
• Authoring and maintaining support processes, documentation, and guides.
• Collaborating with QA and Engineering teams to drive improvements in our AI services.
• Continuously improve our support processes, tooling and methodologies.
• Participate in a global, follow-the-sun 24x7 on-call rotation.

Required Skills And Experience

• Proven experience working with OpenAI, Anthropic, and other vendor model offerings.
• Hands-on experience with Retrieval Augmented Generation and Vector databases.
• In-depth experience configuring, administering, and troubleshooting Cursor and Claude Code.
• Proficiency in both coding and debugging languages such as Python or Java.
• Has supported and maintained FastAPI based services.
• Familiarity with linux and container runtime environments like Kubernetes.
• Expertise in implementing and improving devops release pipelines.
• Expertise in implementing effective alerting processes with Rootly or similar.
• Proficiency with instrumenting monitoring with Datadog, Langsmith, or Pydantic.
• Excellent problem-solving and analytical skills with a detail-oriented approach.
• Demonstrates a clear sense of ownership in driving issues to resolution.
• Strong communication and collaboration skills.

Desired Skills And Experience

• Experience with cutting edge AI Performance Monitoring instrumentation techniques.
• Experience with solving Vector Database challenges at scale, including embedding/retrieval performance and availability.
• Familiarity with various LLM models and architectures with an ability to address issues like model response latency or time to first token.
• Adept at using AI tools like claude code, mcp, and agents to improve our own troubleshooting and support processes.

Key skills/competency

• AI Software
• LLM
• Technical Support
• Troubleshooting
• Python
• Kubernetes
• FastAPI
• Datadog
• Incident Management
• Retrieval Augmented Generation