AI Chatbot Engineer

This role is initially a short-term contract that could become a permanent position in the future.

We’re looking for an engineer to take ownership of our AI orchestration layer for real-time AI character interaction products used in conversational attractions and live experiences. You’ll evolve the foundations built by our partner and bring the system fully in-house — focusing on latency, reliability, multi-routine orchestration, guardrails, and real-time character interaction.

This is a lead-level role for someone excited to own Slacker Apps’ AI systems, stay close to the latest advancements in the AI space, and work hands-on with our team to turn cutting-edge technology into AAA-quality products for world-known clients.

Responsibilities

• Maintain and expand our LLM-based orchestration layer (routing, routines, memory, intent handling).
• Design robust conversation flows with guardrails suitable for public-facing attractions.
• Integrate STT, TTS, RAG, and animation triggers for real-time character interactions.
• Work closely with Unity developers, designers, and animators to deliver low-latency, expressive character experiences.
• Optimise systems for both on-prem and off-prem GPU deployment (4090/5090 boxes, RunPod-style orchestration).
• Evaluate new models, tools, and approach

Requirements

• 2+ years professional development experience required
• Strong backend engineering experience in Python or Node.js.
• Hands-on experience integrating LLMs (OpenAI, Anthropic, fine-tuned models, vector databases).
• Experience building real-time or low-latency systems.
• Solid understanding of GPU-based inference and local/remote deployment strategies.
• Ability to design systems that are stable, observable, and maintainable in production environments.

Nice to haves

While not specifically required, tell us if you have any of the following.

• Experience leading or owning AI systems in production.
• Familiarity with real-time audio pipelines (STT/TTS streaming).
• Experience with character-driven or conversational UX (games, virtual humans, chatbots, assistants).
• Knowledge of prompt engineering, fine-tuning workflows, or evaluation tooling.
• Experience with containerisation, orchestration, or scalable inference infrastructure.
• Interest in AI safety, guardrails, and content moderation for public-facing products.
• Curiosity and enthusiasm for staying up to date with the rapidly evolving AI landscape.

Compensation

¥5,000,000 ~ ¥8,000,000 annually.