Plaud Backend Engineer at Plaud designing and operating batch transcription and streaming ASR API services. Own full stack from API design to deployment and customer support for AI/ML-serving backend.
Responsibilities
Design, build, and ship the batch transcription and streaming ASR API services on Plaud's developer platform — owning the full stack from inference API design and model service integration through authentication, rate limiting, versioning, and developer documentation.
Deploy and operate the STT services across all 4 global regions; establish on-call rotation, monitoring, alerting, and SLO governance from launch; lead incident response and post-mortems.
Architect for high-concurrency, low-latency MaaS-style workloads — streaming/real-time protocols (WebSocket/gRPC), async job pipelines for batch transcription, autoscaling, and cost/latency optimization — benchmarking against SOTA inference API providers (e.g., Deepgram, AssemblyAI, Google STT).
Serve as the primary technical point of contact for B2B customers on API capabilities; scope, commit to, and deliver new feature requests on defined timelines.
Collaborate directly with the algorithm team on ASR model integration and with product on the developer platform roadmap; use AI tooling to accelerate development, documentation, and observability workflows.
Qualification
Required
3+ years of backend engineering experience with strong Go (Golang) proficiency; shipped and operated production services in Go.
Hands-on production experience building and operating AI/ML-serving backend services — inference API design, model service integration, on-call and incident response — not just internal tooling or prototypes.
Solid architecture experience with high-concurrency, low-latency platform services: multi-region deployment, streaming/real-time protocols (WebSocket and/or gRPC), async/queue-based job pipelines, and autoscaling.
Experience designing and shipping public-facing APIs or SDKs — authentication, rate limiting, versioning, and developer-facing documentation.
Professional English proficiency (written and spoken) for developer documentation and direct B2B customer engagement.
