AI Engineer (Full-time) — O₂ AI

🌍 Remote, USA 🎯 Full-time 🕐 Posted Recently

Job Description

Just as Harvey is transforming the legal industry, O₂ AI is building a Vertical AI Agent for the global semiconductor and electronics supply chain.

Company Website:

We build deeply vertical AI Agents capable of handling high-stakes, high-complexity challenges in global manufacturing systems, transforming chaos into efficient, intelligent automated execution.

We are looking for a hands-on Full-time Builder to own product engineering end-to-end: delivering core features, improving system reliability, and continuously expanding applications and the AI workflows behind them.

Why Join Us'Elite Founding Team

Work alongside founders from Yale, UC Berkeley, Stanford, and MIT, who bring both world-class academic foundations from top research labs and real-world "battle scars" from industry frontlines. Gain continuous access to firsthand insights and perspectives from Silicon Valley's startup and technology frontier.

Real Customers, Real Impact

At O₂ AI, we provide you with direct opportunities to communicate with customers. You will interface directly with US clients and collaborate with Fortune 500 electronics and semiconductor companies, building production-grade AI Agents that are truly deployed and operational.

True 0 → 1 Ownership

At O₂ AI, we create opportunities for you to deeply engage in product and engineering. You will participate in the complete process from problem definition and solution design to product launch and continuous iteration, gaining highly hands-on practical experience and witnessing the real-world impact of your work in customer business scenarios.

Co-creating Cutting-edge AI with MIT

O₂ AI collaborates deeply with MIT Media Lab to advance frontier AI research in real industrial scenarios, with opportunities to conduct joint research with the MIT team, publish papers, and translate research outcomes into production-grade vertical AI Agents.

What You'll Work On (Core Responsibilities)

End-to-end product and engineering development: From requirement understanding → architecture design → implementation → deployment → iteration, lead the complete product lifecycle

Context Engineering, RAG (Retrieval-Augmented Generation)
Tool / Function calling, security and risk controls
Agent behavior evaluation, failure mode analysis and optimization

Authentication, role/permission systems
Data model design and optimization
Multi-tenant architecture
System scalability and performance optimization

REST API design and implementation
SQL Schema design, index optimization
Database performance tuning
Caching strategies and implementation

Build modern UI with React + TypeScript
Implement complex interactions and state management
Optimize frontend performance and user experience

Docker containerization deployment
Cloud service configuration and management (AWS/GCP/Azure)
CI/CD pipeline construction
System monitoring, log analysis, and troubleshooting

Participate in technology selection and architectural decisions
Code Review and technical standards development
Technical debt management and refactoring

Directly communicate requirements with US customers
Technical solution demos and explanations
Collect feedback and iterate rapidly

What We're Looking ForRequired Skills

Data structures and algorithms
System design and architecture
Networking and distributed systems basics

Frontend: React + TypeScript, modern frontend engineering practices
Backend: Python / Node.js, able to build scalable services
At least 2-3 years of practical development experience (or equivalent capability)

Deep understanding of LLM working principles and limitations
Prompt Engineering and Context design
RAG architecture design and implementation
Multi-step reasoning and Agent behavior design

SQL (PostgreSQL / MySQL)
NoSQL (MongoDB / Redis)
Schema design, query optimization

Docker / Kubernetes basics
AWS / GCP / Azure cloud services
CI/CD pipelines (GitHub Actions / GitLab CI)

Code quality awareness, writing maintainable and testable code
Git workflow, Code Review capabilities
Documentation and technical communication skills

Able to independently analyze problems, design solutions, implement features
Proactively seek best practices and optimization approaches
Quickly learn new technologies and tools

Able to conduct technical communication with US customers
Read English technical documentation fluently

Strong Bonus Points

Fully participated in or led a SaaS product from 0 to 1
Understand enterprise product complexities: security, permissions, multi-tenancy, billing, etc.

Built and deployed complex AI Agents or LLM workflows
Deep understanding of Agent behavior evaluation, failure modes, reliability assurance

Able to build runnable prototypes in short timeframes (days) to validate ideas
Quickly respond to customer feedback and iterate

Designed high-concurrency, high-availability systems
Practical experience in performance analysis and optimization

High-quality projects or contributions on GitHub
Technical blogs, talks, active in open source communities

Prompt patterns, retrieval, Memory management
Evaluation methods, failure and degradation scenarios
MCP (Model Context Protocol) experience

OpenAI SDK / Anthropic SDK
LangChain / LlamaIndex
Or self-built Agent framework experience

Claude Code, Cursor, GitHub Copilot, etc.
Know how to use them efficiently and responsibly

What You'll Get

Market-rate salary
Early employee equity incentives

Work directly with founding team
Participate in core technical decisions
Access cutting-edge AI technology and real industrial scenarios

Remote or Silicon Valley office
Flexible working hours
Support for technical conferences and learning

Technical expert path: Deep dive into technical domains, become an AI Agent domain expert
Management path: Opportunity to lead engineering teams as the team grows
Product path: Deep involvement in product decisions, become technical product lead

Work Location