AI Engineer

IntelliPro Group Inc. • Palo Alto, CA

20d • $200,000 - $300,000

About The Position

IntelliPro is hiring a hands-on AI Engineer to build production AI coding tools and internal AI products. The role focuses on shipping real AI-powered systems rather than conducting research. The engineer will design and build LLM-powered applications end to end and help promote strong AI engineering practices across the organization.

Requirements

• Bachelor's degree or above in Computer Science, Mathematics, AI, or a related engineering field.
• Recent core engineering experience at a leading AI company or large technology company.
• At least 2 years of hands-on experience building and shipping LLM-powered products in production.
• Experience designing and deploying multi-agent systems and agent architectures, such as ReAct or Plan-and-Execute, in production.
• Deep experience with tool-use patterns, API orchestration, and structured LLM outputs.
• Experience with systematic model evaluation and selection, including frontier and open-source models.
• Experience building or operating AI evaluation and benchmarking frameworks.
• Proficiency with AI coding tools such as Claude Code, Cursor, or Copilot as part of a daily engineering workflow.
• Strong Python engineering skills, including building production backends rather than just prototypes.
• Ability to independently scope, build, and ship AI-powered systems end to end.
• Based in the US and able to collaborate effectively across time zones, including APAC, through asynchronous communication.

Nice To Haves

• Chinese language skills.
• Experience applying AI to security, fintech, or crypto domain problems.
• Fine-tuning experience, including LoRA/QLoRA, RLHF, or domain-specific model adaptation.
• Production RAG pipeline experience, including retrieval optimization, chunking strategies, and evaluation.
• Experience building Skills or MCP servers.
• Published work, open-source AI projects, or public technical writing on LLM engineering.

Responsibilities

• Design, build, and ship production LLM-powered products and internal AI tools.
• Design and deploy multi-agent systems and agentic workflows in production.
• Build tool-calling and function-calling workflows, API orchestration, and structured output pipelines.
• Evaluate and select frontier and open-source models based on task performance and cost tradeoffs.
• Build evaluation frameworks, benchmarking, and quality gates for AI systems in production.
• Develop scalable, maintainable AI application backends in Python.
• Partner with product, security, and engineering teams to identify and deliver high-impact AI opportunities.

What This Job Offers

• Job Type: Full-time
• Career Level: Mid Level