Description
fal is hiring an experienced software engineer to build and evolve its core generative media platform infrastructure, including request routing, AI workload orchestration, scheduling, GPU autoscaling, file storage, queueing, and performance tuning. The role focuses on large-scale distributed systems with high traffic and data volume, emphasizing reliability, scalability, observability, and low-latency global performance. Candidates should have strong Python or Rust experience, deep distributed systems knowledge, and a track record of shipping systems under real production load.
