Backend / Platform Engineer

Role Overview Cliply is building a high-throughput, multimodal AI platform that processeslong-form video, audio, and text to generate structured narrative intelligencefor broadcasters and media companies. As a Backend / Platform Engineer, youwill design and operate the distributed systems, media pipelines and model‑servinginfrastructure that power Cliply’s core engine. You will work closely with AI/MLengineers to integrate perception models, multimodal alignment models andLLM/VLM inference services into a scalable production environment. This role iscritical to transforming our AI engine into a reliable, production‑readyplatform. Key Responsibilities Media & AI PipelineEngineering • Build ingestion pipelines for long‑form video, audio and transcripts (multi‑hour content). • Design distributed processing workflows for frame extraction, audio segmentation and metadata generation. • Implement asynchronous job orchestration for long‑running tasks (video processing, multimodal alignment, inference batching). • Integrate GPU‑backed model‑serving endpoints (LLMs, VLMs, perception models) via REST/gRPC. • Build caching, batching and scheduling layers for high‑volume inference workloads. Backend Architecture &Microservices • Design and implement REST/gRPC APIs for content ingestion, retrieval, metadata access and response‑tree execution. • Build microservices that orchestrate multimodal pipelines, queues and background workers. • Implement robust retry logic, backpressure handling and distributed task management. • Develop scalable storage layers for embeddings, metadata graphs, timelines and multimodal outputs. Cloud Infrastructure &Deployment • Architect and operate cloud environments (AWS/GCP) for development, staging and production. • Deploy containerised services using Kubernetes (EKS/GKE) for microservices and model serving. • Implement CI/CD pipelines for backend and ML components, including automated tests and blue‑green deployments. • Manage object storage (S3/GCS) for large media assets and multimodal datasets. Observability, Reliability& Security • Implement monitoring, logging and tracing for long‑running pipelines and inference services. • Build dashboards for pipeline health, throughput, latency and failure analysis. • Ensure security best practices across authentication, authorisation, rate limiting and usage tracking. • Conduct performance tuning for high‑throughput, low‑latency workloads. Collaboration & SystemDesign • Work closely with AI/ML engineers to integrate perception and multimodal models into backend workflows. • Collaborate with frontend engineers to expose APIs and support creative‑workflow features. • Participate in architecture reviews, design discussions and technical roadmap planning. Requirements Must‑Have • 4–7+ years of experience in backend, platform or distributed systems engineering. • Strong proficiency in Python, Go, Java or Node.js/TypeScript. • Experience with microservices, REST/gRPC APIs and asynchronous processing. • Hands‑on experience with distributed queues (Kafka, RabbitMQ, SQS, Pub/Sub). • Experience deploying services on AWS or GCP (EKS/GKE, EC2/Compute Engine, S3/GCS). • Strong understanding of scalability, reliability, concurrency and fault‑tolerance. • Experience with Docker, Kubernetes and CI/CD pipelines. • Familiarity with large object storage and high‑volume data pipelines. Nice‑to‑Have • Experience integrating ML model‑serving frameworks (Triton, TorchServe, custom gRPC). • Experience with GPU scheduling, inference batching or multimodal pipelines. • Experience with media processing (FFmpeg, video/audio extraction, streaming APIs). • Experience with observability stacks (Prometheus, Grafana, OpenTelemetry). • Cloud certifications (AWS/GCP) or prior experience with high‑throughput systems. Why Cliply • Build the core engine of a next‑generation multimodal AI platform for the media industry. • Work directly with senior AI engineers on perception, multimodal alignment and long‑form reasoning. • Solve complex distributed‑systems challenges at the intersection of media, AI and cloud infrastructure. • Join a pre‑seed team where your work directly shapes the product, architecture and future of the company.