Inflection AI
Principal Engineer, Agentic AI Systems
$400K–$550K
Palo Alto, California, United States · Principal · Full-time · Posted Jun 29, 2026
- Experience
- 10+ years of engineering experience; includes 3+ years at staff/principal or equivalent scope and 2+ years building production-grade agentic or LLM-powered systems used by real customers.
- Education
- Bachelor’s degree or equivalent in a related field to the offered position requirements.
- Visa sponsorship
- Support of country-specific visa needs for international employees living in the Bay Area.
About the job
Leads the architecture and technical direction of production agentic AI systems, from agent design and evaluation to reliability and shipped AI-powered features.
What you'll do
- Build production agents that plan, retrieve context, use tools, take actions, and recover from failures; design their architectures and safety controls.
- Create evaluation, observability, and reliability systems, and integrate agents with APIs, databases, enterprise tools, and user workflows.
- Set technical direction and engineering standards, collaborate across product, design, and engineering, and coach the team.
What they ask for
- 10+ years of engineering experience, including 3+ years at staff/principal or equivalent scope and 2+ years building production-grade agentic or LLM-powered systems used by real customers.
- Strong Python or TypeScript experience.
- Experience with LLM-powered products or systems, backend engineering, and tool/function calling, structured outputs, retrieval, prompt design, and model evaluation.
- Bachelor’s degree or equivalent in a related field to the offered position requirements.
Nice to have
- Experience with LangGraph, LlamaIndex, OpenAI, Anthropic, Hugging Face, vLLM, or similar tools.
- Experience with agent memory, planning, multi-agent systems, automation, evaluation pipelines, observability, guardrails, or AI safety.
Pay
USD 400,000.00 to USD 550,000.00 base salary
Tools
Python, TypeScript, LangGraph, LlamaIndex, OpenAI, Anthropic, Hugging Face, vLLM
AI focus
Builds production agents and agentic AI systems, including architecture, tool use, retrieval, evaluation, observability, reliability, and safe execution.
Model-written summary · the original posting is authoritative