The vacancy is strong in task clarity and requirements but lacks compensation details and company information.
no company info
Job description
We are looking for a Senior AI Engineer to build production AI infrastructure for content generation, focusing on video and image processing. Strong Python and FastAPI skills are required.
Responsibilities
### Responsibilities
- Develop AI pipelines: text → image, image → image, text → video, video → video.
- Integrate and optimize: SDXL, Flux, Stable Diffusion, ControlNet, LoRA.
- Work with video generation and multimodal AI systems.
- Build production inference: GPU scheduling, batching, caching, queues, streaming, latency/throughput optimization.
- Optimize GPU utilization and inference cost.
- Develop backend/API: Python, FastAPI, async pipelines, orchestration.
- Set up monitoring, observability, alerts, metrics.
Requirements
### Requirements
- Strong Python / FastAPI.
- Production experience: Generative AI / Diffusion / Video Generation.
- Experience with: SDXL / Flux / Stable Diffusion / ControlNet / LoRA.
- Understanding of: inference pipelines, batching, latency, throughput.
- Experience with GPU infrastructure: CUDA ecosystem, VRAM optimization, model serving.
- Basic MLOps: deployment, monitoring, model versioning.
- Nice to have: TensorRT / ONNX / vLLM.
- Kubernetes / Docker / Redis / PostgreSQL.
- RabbitMQ / Kafka / Celery.
- Fine-tuning / LoRA training.
- Highload AI systems.