Python Engineer (LLM)
HAKEN: (Only for candidates residing in Japan) Build revolutionary AI chatbots and automated leadership analytics for Japan’s premier coaching firm.
Responsibilities
- Develop and refine an advanced AI coaching chatbot to provide real-time, context-aware leadership guidance.
- Architect automated report generators that analyze client data to produce sophisticated leadership insights.
- Build a suggestion engine that leverages LLMs to provide coaches with high-impact, data-driven questions.
- Integrate vector databases and embedding models to maintain deep conversational memory and client context.
- Deploy and scale these AI services using Docker to ensure high availability across the coaching platform.
Requirements
- Current residency in Japan is mandatory (Domestic applicants only).
- Strong Python expertise with experience building production-level backend systems.
- Hands-on with web frameworks, specifically utilizing FastAPI or Django for API development.
- Direct experience with LLMs, including prompt engineering and managing RAG (Vector DB) architectures.
- Proficiency in Docker for containerizing and deploying complex AI microservices.
Desired Skills
- Experience with NLP sentiment analysis to better understand client emotional cues.
- ML frameworks such as TensorFlow, PyTorch, or Scikit-learn for model fine-tuning.
- Familiarity with Cloud Infrastructure for hosting Large Language Models.
- Previous work on Chatbot/Conversational AI UI/UX flows.
- Knowledge of Data Visualization libraries for leadership report generation.