[Remote] Senior Machine Learning Engineer

Note: The job is a remote job and is open to candidates in USA. SilverSearch, Inc. is a globally recognized media and information organization, and they are seeking a Senior Machine Learning Engineer to build and optimize large-scale ML inference systems. This role focuses on production-scale inference optimization and ML infrastructure, requiring hands-on experience in a highly technical environment.

Responsibilities

• Design, build, and optimize large-scale ML inference systems for text, image, and video workloads
• Scale semantic/vector search and embedding pipelines across millions of media assets
• Optimize inference latency, throughput, and cost efficiency for production ML systems
• Work with transformer-based NLP and computer vision models in production environments
• Improve and operationalize multimodal AI pipelines using existing/open-source models
• Build scalable data processing systems across CPU/GPU cloud infrastructure
• Partner closely with Data Science and Platform teams to productionize ML workflows
• Contribute to hybrid search and retrieval systems using vector search and reranking approaches
• Monitor and improve performance, reliability, and efficiency across distributed ML workloads

Skills

• 8+ years of experience building production ML systems
• Strong experience optimizing ML inference performance in production
• Hands-on experience with: PyTorch
• Hands-on experience with: TensorFlow
• Hands-on experience with: ONNX / TorchScript
• Hands-on experience with: Transformer-based NLP models
• Experience building or supporting semantic/vector search systems
• Experience deploying ML systems in AWS cloud environments
• Strong understanding of distributed processing and scalable ML pipelines
• Experience with multimodal workloads involving text, image, or video processing
• Familiarity with embedding generation and retrieval systems
• Video processing experience (highly preferred)
• Experience with large-scale inference optimization
• Familiarity with reranking systems and hybrid search architectures
• Experience with HuggingFace models and modern ML tooling
• Experience optimizing GPU-based workloads
• Familiarity with multimodal AI APIs and services

Benefits

• Fully remote
• Preference for East Coast collaboration hours
• 6-month contract-to-hire

Company Overview