Staff AI Engineer

Overnox; United States; Remote; USD 180,000 - 260,000; Full time

Job summary

Overnox is seeking a high-impact leader to define the technical direction for production-grade LLM systems, covering agents, retrieval-augmented generation, and evaluation pipelines for demanding enterprise environments. You will mentor engineers, architect scalable solutions, and partner with cross-functional teams to translate business requirements into reliable AI capabilities and durable production quality.

This role is a bar-raiser for engineering culture.

Qualifications

• Extensive experience shipping LLM-based systems to production at scale.
• Deep understanding of agents, RAG pipelines, and evaluation methodologies.
• Strong software engineering fundamentals with emphasis on reliability and operability.
• Proven ability to set technical direction and influence engineering culture.
• Experience operating complex AI systems in demanding customer environments.

Responsibilities

• Define and continuously raise the technical bar for production LLM system design and operations.
• Architect solutions across agent workflows, RAG pipelines, and evaluation frameworks.
• Guide the path from prototype to reliable production for enterprise use cases.
• Establish engineering patterns and review practices adopted by the broader team.
• Partner with cross-functional peers to translate business requirements into working AI capabilities.
• Mentor engineers and contribute to long-term technical strategy.

Skills

Production LLMs

Agents

RAG pipelines

Evaluation methods

Reliability

Operability

Technical leadership

Job description

Role overview

Set the technical direction for how production-grade large language model systems are designed, shipped, and operated. The work spans agents, retrieval-augmented generation, and evaluation pipelines intended for demanding enterprise environments, with the role acting as the bar-raiser for engineering quality across these efforts.

Responsibilities

• Define and continuously raise the technical bar for production LLM system design and operations


• Architect solutions across agent workflows, RAG pipelines, and structured evaluation frameworks


• Guide the path from prototype to reliable production for enterprise use cases


• Establish engineering patterns and review practices adopted by the broader team


• Partner with cross-functional peers to translate business requirements into working AI capabilities


• Mentor engineers and contribute to long-term technical strategy

Requirements

• Significant experience shipping LLM-based systems to production at scale


• Strong working knowledge of agents, retrieval-augmented generation, and evaluation methodologies


• Deep enterprise software engineering fundamentals, including reliability and operability


• Demonstrated ability to set technical direction and influence engineering culture


• Track record operating complex AI systems in demanding customer contexts