Python Engineer

We're seeking experienced Python Engineers with expertise in building modern AI systems, particularly focusing on Retrieval Augmented Generation (RAG) architectures and agentic AI frameworks. The ideal candidate will have strong experience with FastAPI, vector databases, and orchestrating complex AI agents to solve real-world problems. As a Python Engineer at UltraSafeAI, you'll work on designing and implementing scalable, secure AI systems that power our clients' critical business processes. You'll collaborate with a global team of engineers, researchers, and domain experts to create solutions that set new standards for safety and reliability in AI. Key Responsibilities: ● Design and develop robust FastAPI applications that serve as the backbone for our AI systems ● Implement sophisticated RAG (Retrieval Augmented Generation) architectures utilizing vector databases, embeddings, and reranking techniques ● Build and orchestrate multi-agent AI systems using frameworks like LangGraph, CrewAI, or Agent Development Kit ● Develop intelligent knowledge retrieval systems that enhance LLM capabilities with domain-specific information ● Create scalable, maintainable, and well-tested code that meets our high-quality standards ● Contribute to architecture decisions and technology selection for new projects ● Collaborate with cross-functional teams to understand requirements and deliver solutions ● Participate in code reviews and knowledge sharing to elevate the entire engineering team ● Stay current with the rapidly evolving AI landscape and recommend new approaches Required Qualifications: ● Strong expertise in FastAPI development with authentication, async processing, and API design ● Practical experience building RAG systems with vector databases (Pinecone, FAISS, Chroma, Qdrant, etc.) ● Experience with embedding models and techniques for effective information retrieval ● Hands-on experience with at least one agentic framework (LangGraph, CrewAI, Agent Development Kit, etc.) ● Solid understanding of LLMs and their integration into production systems ● Excellent problem-solving skills and attention to detail ● Strong communication skills and ability to work in a distributed team ● Self-motivated with the ability to work independently in a remote environment Highly Desirable: ● Experience with specialized vector database operations and optimizations ● Knowledge of reranking techniques to improve retrieval quality ● Experience building complex multi-agent systems that coordinate specialized AI agents ● Background in specific domains like finance, healthcare, or legal ● Contributions to open-source projects ● Understanding of AI safety considerations and alignment techniques ● Experience with deployment and monitoring of AI systems in production

UltraSafeAI is a US-based technology company at the forefront of developing secure, reliable, and explainable AI systems. We specialize in proprietary AI technologies including advanced LLMs, CNNs, VLLMs, intelligent agents, computer vision systems, and cutting-edge ML algorithms. Our focus is on B2B AI adoption, providing end-to-end integration using our proprietary technology stack to automate entire business processes. We create intelligent solutions that prioritize safety, transparency, and human alignment across various industries including healthcare, finance, legal, and enterprise services. Our mission is to enable seamless AI adoption while maintaining the highest standards of safety and ethical considerations.