Senior AI Engineer

Summary

Join our team as a Senior AI Engineer and help build IrisGo, an AI butler for the AI PC era. You will lead the design and development of advanced AI systems, from prototyping to scaling production systems. This role requires extensive hands-on experience with Large Language Models (LLMs) and Generative AI. You will architect and implement scalable AI systems, lead end-to-end development efforts, prototype and deploy GenAI applications, and contribute to model selection and improvement. The ideal candidate possesses a strong full-stack background, a product-driven mindset, and a passion for applying cutting-edge AI in user-focused ways.

Requirements

• 4+ years of experience working in ML or AI engineering roles, ideally with a focus on NLP or GenAI
• Deep understanding of how modern LLMs work, including transformer architectures, finetuning, and evaluation
• Hands-on experience implementing and optimizing GenAI techniques such as: Tool/function calling, Multi-agent workflows, Retrieval-Augmented Generation (RAG), Finetuning or custom training (e.g., LoRA, PEFT), and Structured prompting and evaluation
• Proficiency with GenAI frameworks and tools (e.g., LangChain, LlamaIndex, Hugging Face, Haystack)
• Experience integrating LLMs into real-world applications, including building internal tooling or customer-facing AI features
• Solid foundation in full-stack development or backend systems (Python, TypeScript, FastAPI, etc.)
• Experience designing and deploying scalable APIs and cloud infrastructure (AWS, GCP, or Azure)
• Proficient with databases (PostgreSQL, MongoDB, or vector DBs like Pinecone or Weaviate)
• Comfortable working in agile product teams and balancing experimentation with shipping reliable code
• Strong Git/GitHub collaboration skills and comfort working with CI/CD workflows and containerization (Docker, etc.)

Responsibilities

• Architect and implement scalable AI systems and applications powered by LLMs and multi-agent frameworks
• Lead end-to-end development efforts, including model integration, infrastructure design, and application logic
• Prototype and deploy GenAI applications that combine retrieval, tool use, reasoning, and interactivity
• Contribute to decision-making around model selection, finetuning, evaluation, and safety mechanisms
• Monitor AI/ML performance in production and drive continuous improvement of prompt, RAG, and agent pipelines
• Stay at the forefront of GenAI developments and bring innovative ideas into the product roadmap

Preferred Qualifications

• Experience working in a startup or research-oriented environment
• Prior exposure to open-source AI models (e.g., LLaMA, Mistral, Mixtral) and fine-tuning them
• Publications, technical blog posts, or demos of past AI work