Job Description
Are you ready to architect the future of autonomous intelligence? Zai Future Labs is pioneering the next generation of Agentic AI systems designed for 2026 and beyond. We are looking for a visionary Senior Architect to build the neural foundations of self-evolving software agents.
In this role, you won't just manage models; you will engineer Autonomous Workflows, enable Long-term Memory, and create Reasoning Loops that outperform traditional static algorithms. If you are passionate about pushing the boundaries of Large Language Models (LLMs) and creating systems that act with intent, this is your opportunity to lead the charge.
Why Join Us?
- Work on cutting-edge 2026-ready technology stacks.
- Competitive compensation and equity packages.
- Remote-first culture with a collaborative HQ in San Francisco.
Responsibilities
- Architect Autonomous Agents: Design and implement complex multi-agent systems capable of autonomous decision-making and task execution.
- Orchestrate LLM Workflows: Build robust pipelines that integrate LLMs with external tools, databases, and APIs for seamless execution.
- Optimize Inference Latency: Engineer high-performance inference systems to handle real-time autonomous interactions at scale.
- Develop Memory & Reasoning: Create sophisticated memory architectures that allow agents to retain context and learn from interactions over time.
- Ensure Ethical Alignment: Implement guardrails and safety protocols to ensure AI behavior aligns with ethical standards and user intent.
Qualifications
- Education: Master’s degree in Computer Science, Artificial Intelligence, or a related technical field.
- Experience: 5+ years of professional experience in software engineering with a focus on AI/ML.
- Core Tech: Deep expertise in Python, PyTorch, or TensorFlow.
- Framework Mastery: Proven experience with LangChain, LlamaIndex, or similar agent orchestration frameworks.
- Data Engineering: Strong understanding of vector databases (e.g., Milvus, Pinecone) and RAG (Retrieval-Augmented Generation) architectures.