About the company
Fast-growing AI product in the adult entertainment space. The product combines AI companions, conversational AI, image/video generation and subscription-based monetization. You’ll join the AI team building the intelligence behind the product and work closely with backend, product and QA teams.
Responsibilities
- Develop and maintain parts of the AI/chat pipeline: prompt construction, character personality, memory, context and response processing.
- Integrate and evaluate LLM, image and video generation providers, comparing quality, cost and latency.
- Train and retrain LoRAs for character consistency across image and video generation.
- Build multi-step AI/agentic workflows for content generation, including automated validation.
- Run structured prompt experiments and evaluations using tools such as Langfuse.
- Manage inference infrastructure pragmatically: GPU providers (RunPod and similar), provider migrations, worker handlers, and cost/latency optimization.
Requirements
- 3+ years of professional Python development, including production backend services, async patterns, queues, microservices.
- Hands-on experience integrating LLMs or Generative AI models into production — prompt engineering, structured outputs, fallback logic and handling model failures.
- Practical experience with diffusion models and LoRA — training/fine-tuning, checkpoint evaluation (SDXL or similar) or image-to-video generation.
- Experience building multi-step AI/agentic workflows (chained generation, tool use, automated validation).
- Production experience with Docker, CI, GPU inference providers (RunPod, fal.ai or similar), monitoring and debugging.
- Good written and spoken English.
Conditions
- Competitive salary
- Office-based role in Limassol, Cyprus