What are the responsibilities and job description for the Staff AI Engineer position at Tandym Tech?
An enterprise media technology organization is seeking a Staff AI Engineer for a remote role focused on building and scaling advanced AI systems for enterprise content scanning and research. The position centers on LLMs, AI agents, agentic workflows, and production-grade Python and AWS development.
About the Opportunity:
Shift: Day shift
Schedule: Monday through Friday
Hours: Standard business
Setting: Remote
Responsibilities:
Design and build agentic systems, including tool use, multi-step workflows, reasoning, streaming, and state management.
Develop and operate production APIs and services, with attention to reliability, scalability, authentication, and backward compatibility.
Build backend AI systems that support enterprise workflows across orchestration, retrieval, evaluation, and observability.
Evaluate AI system quality, reliability, and safety using structured datasets, regression testing, and production monitoring.
Contribute to full-stack product experiences when needed and collaborate across engineering on pragmatic, production-ready solutions.
Qualifications:
7 years of programming experience in one or more modern languages such as Python, Java, Golang, or JavaScript
5 years of experience shipping production software in an enterprise or consumer environment
2 years of experience architecting, designing, and optimizing search and information retrieval systems at scale
6 months to 1 year of hands-on experience building agentic products or solutions
1 year of experience evaluating AI systems for quality, reliability, and safety at scale
Strong backend engineering fundamentals and experience working with APIs, batch workflows, orchestration, observability, and production support
Experience working with AWS
BS in Computer Science, Electrical Engineering, or equivalent experience
Desired Skills:
Experience with modern agent frameworks such as OpenAI Agents SDK, LangGraph, Google ADK, or SmolAgents
Experience with OpenSearch or Elasticsearch
Experience with foundation models, open-source LLMs, and model evaluation techniques
Exposure to AI orchestration frameworks, retrieval strategies, and multimodal systems
Experience with JavaScript/TypeScript and React
Experience with Docker, Kubernetes, CI/CD, or Azure
Experience with media-processing tools such as FFmpeg or OpenCV