We are seeking a highly skilled Python AI Backend Engineer to design and implement intelligent, high-availability AI systems, including Agent-based conversational AI and Retrieval-Augmented Generation (RAG) solutions. You will play a key role in building scalable, efficient, and cutting-edge AI infrastructure to power our next-generation applications.
Key Responsibilities:
- Design and implement high-performance AI dialogue systems and RAG architectures for optimal scalability and reliability.
- Develop AI Agents and Memory recall mechanisms to enhance contextual understanding and response quality.
- Build hybrid retrieval systems combining semantic search and keyword search for improved accuracy and recall.
- Design and develop AI APIs (e.g., OpenAI-based interfaces) with a focus on stability, latency, and extensibility.
- Continuously optimize RAG performance metrics, including recall rate, precision, and response time.
- Collaborate with cross-functional teams to integrate AI solutions into production systems.
Qualifications:
- Bachelors or higher degree in Computer Science or a related field.
- 5+ years of Python development experience, with clean, maintainable coding standards.
- 1+ years of hands-on AI experience, with familiarity in AI Agent frameworks and rapid prototyping of AI applications.
- Deep understanding of LLM workflows, Tools/Tool Calling, OpenAI API standards, and Prompt Engineering.
- Experience with RAG systems, vector databases (e.g., FAISS, Pinecone, Weaviate), and retrieval optimization.
- Proficiency in LangChain, LlamaIndex, or similar LLM development frameworks.
- Expertise in FastAPI/Flask and backend systems design for high-concurrency environments.
- Strong knowledge of databases (PostgreSQL/MySQL), caching (Redis), message queues, and MongoDB.
- Experience with microservices architecture and distributed systems.
Bonus Points:
- Contributions to open-source AI projects.
- Experience with Docker/Kubernetes for containerized deployments.
