The role involves architecting and operating scalable backend services for a global media intelligence platform that processes text, image, video, and audio content
Job Summary
The role involves architecting and operating scalable backend services for a global media intelligence platform that processes text, image, video, and audio content.
Candidates will lead the development of AI/ML workflows including scene detection, transcription, embedding generation, and multimodal inference within production environments.
This position requires deep expertise in optimizing model inference for latency and cost while ensuring high-throughput asynchronous processing patterns.
Matching Summary
The role involves architecting and operating scalable backend services for a global media intelligence platform that processes text, image, video, and audio content.
Skills & Requirements
Must-have
5-7+ years backend engineering experience
3+ years AI/ML integration experience
Python or Node.js expertise
Distributed system architecture design
Vector search and semantic retrieval
Media processing pipeline development
Nice-to-have
Experience with vLLM or Triton model serving
Knowledge of PyTorch and TensorFlow frameworks
Mentoring junior engineers
Cloud infrastructure deployment on AWS/GCP
Multimodal model optimization techniques
Key Requirements
Bachelor's degree in Computer Science or equivalent