Job Summary:
The AI Engineer will design, develop, deploy, and maintain next-generation AI-powered applications using Python, FastAPI, React, TypeScript, and cloud-based AI services. The role requires end-to-end ownership of production-grade Generative AI systems, including architecture, development, deployment, operational readiness, production support, observability, and cost optimization. The ideal candidate will have strong full-stack engineering expertise combined with hands-on experience in LLMs, agentic workflows, RAG, AI orchestration, and modern cloud-native technologies. This is an onsite position in San Francisco, California.
Key Responsibilities:
• Design, develop, deploy, and maintain AI-powered applications using Python, FastAPI, React, TypeScript, and cloud-based AI services.
• Own assigned AI systems end-to-end, including architecture, development, deployment, operational readiness, production support, and cost optimization.
• Implement GenAI patterns including prompt engineering, Retrieval-Augmented Generation (RAG), multi-agent architectures, and workflow orchestration.
• Adopt AI-augmented software development practices and utilize AI coding assistants.
• Partner with architects, engineers, and product teams to define and implement technical solutions.
• Provide technical mentorship and guidance on agentic development practices, AI tooling, and prompt engineering.
• Build and maintain AI system observability solutions, including tracing, token usage tracking, cost management, and performance monitoring.
• Perform coding, testing, troubleshooting, and implementation of software enhancements across the full stack.
• Drive delivery of AI initiatives while managing multiple priorities and competing demands.
• Support CI/CD processes and deployment activities, including occasional off-hours deployment support as needed.
Required Qualifications:
• Bachelor's or master's degree in Computer Science, AI/ML, Information Technology, or equivalent experience.
• 5+ years of software engineering experience, including 2+ years focused on AI/ML or Generative AI applications.
• Proven experience delivering production AI systems with end-to-end ownership.
• Hands-on experience developing production-grade Generative AI applications.
• Strong understanding of LLM architectures, prompt engineering, agentic workflows, RAG frameworks, and AI orchestration patterns.
• Experience with AI platforms and models such as Google Vertex AI, Gemini, Anthropic Claude, or OpenAI models.
• Expert-level proficiency with AI coding assistants such as GitHub Copilot, Claude Code, or Cursor.
• Familiarity with LLM observability and tracing solutions such as LangFuse and LangSmith.
• Strong proficiency in Python, FastAPI, asynchronous programming, Pydantic, and SQLAlchemy ORM.
• Experience with React, TypeScript, and state management frameworks such as Zustand.
• Experience with PostgreSQL, MySQL, query optimization, and database migrations.
• Strong understanding of Docker, Kubernetes, container orchestration, and CI/CD pipelines.
• Experience with cloud platforms such as Google Cloud Platform, Cloud Run, and BigQuery.
• Experience implementing OAuth 2.0, JWT authentication, and Role-Based Access Control (RBAC).
Preferred Qualifications:
• Experience building enterprise-scale AI platforms or internal developer tools.
• Experience supporting AI applications in production environments.
• Familiarity with AI governance, model evaluation, and responsible AI practices.
• Ability to mentor engineers and influence technical direction within a team.
• Strong communication and stakeholder management skills.
• Experience with Agile methodologies and related tools.
• Retail industry experience.
