Lead Engineer, AI Platform
Skills
About the Role
You will design and implement production AI systems with an emphasis on reliability, observability, and continuous evaluation. You will lead development of natural-language interfaces to business data and architect multi-agent systems that coordinate across data sources. You will build evaluation harnesses and testing frameworks to measure AI quality before production deployment. You will translate complex requirements into scalable AI solutions, mentor engineers, establish coding standards, and partner with data engineering to define and enforce semantic models.
Requirements
- 5+ years building production AI/ML systems with experience deploying LLM-based applications beyond proof-of-concept
- Hands-on experience with agent frameworks, tool-use patterns, and multi-step reasoning systems
- Experience with at least three of: LangChain, LangGraph, LlamaIndex, multi-agent frameworks, Model Context Protocol, DSPy, vector databases, structured output libraries, LLM inference infrastructure, cloud AI platforms, or evaluation and observability tools
- Strong background in data engineering, semantic modeling, or analytics infrastructure
- Proficiency in Python for AI/ML and cloud infrastructure (GCP preferred)
- Track record with CI/CD for ML, experiment tracking, and model governance
- Strong communication and ability to present to senior stakeholders
Responsibilities
- Design and implement production AI systems with emphasis on reliability, observability, and continuous evaluation
- Lead development of natural-language interfaces to business data
- Architect multi-agent systems and agent orchestration
- Build evaluation harnesses and testing frameworks measuring groundedness and factual consistency
- Translate complex requirements into scalable AI solutions with clear success metrics
- Mentor engineers and establish coding standards
- Partner with data engineering to define and enforce semantic models