Summary
A growing startup IT company is seeking a highly skilled AI Application Engineer to join their team. The ideal candidate will play a key role in designing, developing, and deploying API services powered by Large Language Models (LLMs) while integrating seamlessly with existing TypeScript-based backend systems.
Essential Duties
- Design, develop, and deploy a Python-based API server with LLM
- Build API endpoints using FastAPI
- Implement LLM workflows using LangChain/LangGraph libraries
- Develop vector search functionality with Qdrant DB
- Implement real-time communication with the frontend using WebSockets
- Effectively integrate with the existing TypeScript backend
- Optimize LLM functionality for performance and cost
- Collaborate with team members to improve the overall system
Working Hours, Working style
Monday - Friday; 8 hours a day
Core hours: 9:30 AM - 2:30 PM (Flexible schedule outside core hours)
Working Location
Irvine, CA
Salary/Benefit
$100K - 140K DOE
- Health insurance
- Retirement plan (simple IRA)
- Paid time off (PTO) & sick leave
Holidays
Saturdays, Sundays, and major US holidays
Qualifications
- Business-level proficiency in English (spoken and written)
- 5+ years of professional experience in Python development
- Proven experience building and deploying production-level applications using LLMs (e.g., GPT, Claude, Azure OpenAI, or Google Gemini)
- Solid understanding of RESTful API design and development
- Experience integrating AI features into real-world applications
- Experience or interest in the following technologies: FastAPI, LangChain / LangGraphQdrant, or other vector databases. WebSocket communication, Basic knowledge of TypeScript and React for integration with frontend systems
- Familiarity with prompt engineering, fine-tuning, or retrieval-augmented generation (RAG)Hands-on experience with OpenAI, Anthropic, or other model APIs in scalable environments
- Awareness of AI safety, latency management, and cost optimization strategies