Senior AI Engineer

About the Company

Amiio is an AI-powered platform built for real estate investors and asset managers. It transforms fragmented financial, technical, and commercial data into clear dashboards and predictive insights—helping real estate professionals optimize performance, reduce costs, and make smarter, faster decisions. Designed for strategic decision-making in real estate, Amiio uses advanced AI to make complex analysis and insights generation fast, intuitive, and fully automated. By combining innovation with intelligence, Amiio is redefining how the industry leverages data and AI—setting a new standard for modern real estate management.

About the Role

We’re looking for a talented and hands-on Senior AI Engineer to lead the development of intelligent systems powering our platform. The ideal candidate is highly proficient in Python, has deep expertise in LLM agents and agentic systems, and is skilled in building custom AI models and advanced RAG architectures.

We’re looking for someone who lives and breathes agentic AI, deeply understands how these systems work beyond existing frameworks, and has experience designing and orchestrating complex multi-agent workflows, reasoning, planning, tool use, memory, and context-aware conversational systems.

You’ll take ownership of designing and implementing advanced AI-driven features, working closely with our product and engineering teams to integrate them into real-world, production-grade solutions.

Responsibilities

• Design and build production-grade LLM-powered agentic and multi-agent systems
• Design advanced agent workflows involving reasoning, planning, tool use, memory, and context management
• Implement custom machine learning models tailored to product needs
• Design and optimize advanced RAG architectures, retrieval strategies, embeddings, and vector search
• Work extensively with structured and unstructured data, including pipeline development, preprocessing, and transformation
• Research, evaluate, and implement state-of-the-art AI models, tools, frameworks, and research
• Develop evaluation methods for LLM and agent performance, accuracy, and reliability
• Collaborate with developers to integrate AI components into the platform
• Monitor and optimize AI systems for performance, scalability, latency, reliability, and cost
• Take end-to-end ownership of complex AI initiatives from research and architecture through production

Requirements

• 5+ years of hands-on experience in AI/ML projects, with strong Python expertise
• Deep expertise in LLM agents and agentic architectures
• Proven experience designing and deploying complex agentic systems in production
• Strong experience with multi-agent orchestration, tool-using agents, agent planning and reasoning, memory, state management, and context-managed conversational agents
• Deep understanding of agent frameworks such as LangGraph, OpenAI Agents SDK, AutoGen, CrewAI, Hugging Face, or equivalent
• Ability to design agent architectures independently rather than relying solely on existing frameworks
• Deep understanding of Retrieval-Augmented Generation (RAG), vector databases, embedding model selection, hybrid retrieval, reranking, and retrieval tuning
• Strong understanding of LLM fundamentals, inference, context management, and model limitations
• Experience with LLM evaluation, monitoring, and performance optimization
• Proven ability to work with large datasets, including data cleaning, transformation, and optimization
• Experience building and integrating APIs such as FastAPI
• Ability to independently research, evaluate, and implement ideas from state-of-the-art AI research
• Self-driven, curious, and capable of independently solving complex technical problems

Nice to Have

• PhD in Computer Science, Artificial Intelligence, Machine Learning, NLP, or a related field – strongly preferred
• Research experience in LLMs, NLP, reasoning, reinforcement learning, or agentic systems
• Familiarity with modern LLM fine-tuning techniques and RL-based optimization methods such as LoRA/QLoRA, PEFT, PPO, DPO, and GRPO
• Understanding of data privacy and security in AI applications
• Experience with cloud platforms such as AWS, GCP, or Azure
• Experience building deployment pipelines for ML/LLM models using Docker, GitHub Actions, Kubernetes, FastAPI, or similar technologies.