Tether /Machine Learning Systems Engineer

Նկարագրություն

Պարտականություններ

• Architect, build, and operate scalable backend services for a media intelligence platform.
• Own backend components from system design and API contracts to deployment and monitoring.
• Design high-throughput media ingestion and processing pipelines.
• Build event-driven workflows using queues and pub/sub systems such as SQS, Kafka, or Pub/Sub.
• Integrate AI/ML services including OCR, speech-to-text, scene detection, embeddings, and multimodal inference.
• Optimize model workflows for latency, throughput, reliability, and cost.
• Work with model-serving systems such as vLLM, Triton, TGI, SageMaker, Vertex AI, or custom inference services.
• Design and maintain vector search and indexing systems using Pinecone, Weaviate, Qdrant, FAISS, pgvector, or similar tools.
• Deploy and operate systems on AWS, GCP, Azure, or similar cloud platforms.
• Ensure reliability through logging, metrics, tracing, alerting, dashboards, and incident-response practices.
• Collaborate with product, design, data, and ML teams.
• Mentor junior and mid-level engineers and support technical planning.

Պահանջներ

• Bachelor’s degree in Computer Science, Engineering, or equivalent practical experience.
• 5–7+ years of backend engineering experience.
• Experience building scalable distributed systems, data pipelines, media platforms, or high-throughput backend services.
• 3+ years of experience integrating AI/ML inference systems into backend workflows.
• Hands-on experience with AI-powered processing pipelines for image, video, audio, or text analysis.
• Strong experience with production model optimization, including batching, caching, quantization, prompt optimization, routing, latency reduction, and cost optimization.
• Experience with vector search, semantic search, media retrieval, or similarity-matching systems is strongly preferred.
• Strong expertise in Python and/or Node.js.
• Strong understanding of scalable RESTful APIs and backend architectures.
• Experience with HuggingFace transformers, PyTorch, or TensorFlow.
• Strong experience with SQL/NoSQL databases, schema design, and data modeling.
• Experience with distributed systems, microservices, asynchronous processing, and event-driven patterns is preferred.
• Experience deploying production systems on AWS, GCP, or similar cloud platforms.
• Strong system design, architecture, observability, and performance engineering skills.
• Excellent English communication skills.

Հմտություններ