Machine Learning Systems Engineer

This is a fully remote position, open to applicants in Sweden.

📋 Description

• Design, construct, and manage scalable backend services for a media intelligence platform, emphasizing clean, maintainable, and production-ready systems.

• Take ownership of essential backend components from system design and API contracts through to implementation, deployment, monitoring, and iterative improvements.

• Influence architectural choices across APIs, processing pipelines, distributed computing, storage, search, observability, cloud infrastructure, and model-serving workflows.

• Create data models and storage architectures for media assets, generated metadata, embeddings, processing tasks, model outputs, search indexes, and audit trails.

• Develop high-throughput media ingestion and processing pipelines to handle large quantities of video, audio, image, and text content.

• Construct distributed, event-driven workflows for media processing utilizing queues and pub/sub systems like SQS, Kafka, Pub/Sub, or similar technologies.

• Implement robust asynchronous processing patterns, including retries, idempotency, dead-letter queues, backpressure management, and fault-tolerant job execution.

• Spearhead the development and enhancement of workflows for metadata extraction, content analysis, scene detection, transcription, embedding generation, and multimodal AI inference.

• Integrate and optimize AI/ML services within backend workflows, encompassing model APIs, embedding pipelines, OCR, speech-to-text, scene analysis, multimodal inference, batching, caching, and fallback strategies.

• Enhance AI/ML inference workflows ensuring low latency, high throughput, reliability, and cost-effectiveness across both real-time and batch-processing scenarios.

• Assess and implement practical model optimization methods such as quantization, model distillation, batching, caching, prompt optimization, and directing tasks to smaller or more cost-effective models when suitable.

• Oversee model and system performance in a production environment, tracking API latency, queue depth, processing times, model error rates, GPU usage, confidence distributions, drift signals, and costs per processed item.

⛳️ Requirements

• Bachelor’s degree in Computer Science, Engineering, or equivalent practical experience.

• 5-7+ years of backend engineering experience, preferably in building scalable distributed systems, media platforms, data pipelines, or high-throughput backend services.

• Previous experience in owning significant backend modules end to end, encompassing architecture, implementation, deployment, monitoring, and production operations.

• 3+ years of experience incorporating AI/ML inference systems into backend workflows, including model APIs, embedding pipelines, OCR, speech-to-text, scene detection, or multimodal model outputs.

• Practical experience in creating AI-driven processing pipelines for analyzing images, videos, audio, or text.

• Hands-on expertise in production model optimization, particularly for image, video, embedding, or multimodal models, including batching, caching, quantization, prompt optimization, routing strategies, latency reduction, and cost optimization.

• Previous experience with vector search, semantic search, media retrieval, or similarity-matching systems is highly preferred.

• Experience in mentoring engineers, leading technical discussions, and influencing architectural decisions across backend, infrastructure, and AI/ML workflows.

🏝️ Benefits

• Flexible work arrangements

• Professional development opportunities

• Equipment allowances