Staff Agentic AI Engineer

Design, build, and improve production-grade AI agentic systems for developing agents on Netomi’s core platform.

Architect agent workflows involving reasoning, tool use, retrieval, guardrails, escalation paths, and performance monitoring.

Evaluate Deep Agent, Claude Agent, OpenAI Agent, LangGraph, and other emerging agent orchestration patterns and frameworks for specific new use cases.

Build and maintain LLM evaluation systems, including LLM-as-judge workflows, regression evals, guardrail testing, quality metrics, and production behavior analysis.

Diagnose agent performance issues across prompts, tool selection, retrieval quality, latency, cost, task completion, and failure modes.

Design and implement RAG and embedding-based capabilities for enterprise knowledge access and automation workflows.

Build scalable Python services and platform components deployed in AWS cloud environments.

Partner with product, platform, and engineering teams to translate emerging agentic AI capabilities into reliable platform features.

Establish engineering best practices for continuous optimization of agentic systems.

Stay current with advances in LLMs, agent architectures, AI coding tools, eval methodologies, retrieval systems, and enterprise automation.

Bachelor’s Degree or higher in a quantitative field (Statistics, Computer Science, Engineering, Mathematics) 

5-7+ years of experience in AI/ML engineering, applied machine learning, natural language processing, and/or AI systems development

2+ years of hands-on experience building production LLM or AI agent systems

Demonstrated experience building agents used in production by external customers or enterprise/business users with hands-on experience using LangGraph, LangChain, or related agent orchestration frameworks.

Experience building systems that turn messy, unstructured source material into validated structured output using schemas, ontologies, or data contracts with entity resolution, disambiguation, and conflict resolution

Strong Python engineering skills and experience building scalable production software systems.

Experience designing agent architectures involving tool use, reasoning flows, retrieval, memory, guardrails, and workflow orchestration.

Experience developing AI evaluation systems, including LLM-as-judge, guardrail evaluation, regression testing, and production quality measurement.

Strong understanding of RAG, embeddings, retrieval quality, and knowledge-grounded generation.

Experience deploying or operating systems in AWS cloud environments.

Daily use of AI coding tools such as Codex, Claude Code, Cursor, or similar tools as part of software development workflows.

Strong engineering judgment, ability to work independently, and comfort operating as a senior individual contributor on ambiguous technical problems.

Master’s Degree or higher in a quantitative field (Statistics, Computer Science, Engineering, Mathematics) 

Experience building or using knowledge graphs for enterprise knowledge modeling, retrieval, reasoning, or personalization.

Experience with enterprise automation platforms, customer experience systems, workflow automation, or AI-powered business process automation.

Familiarity with security, compliance, auditability, and governance requirements for enterprise AI systems.