Search By Location, Search By Postal Code, Search By Location
On-site
Sagemaker pipelines & model monitoring
Gpu/cpu performance & cost optimization
Search infrastructure (elasticsearch/lucene)
Build and maintain SageMaker pipelines for embedding generation and NER workflows, extending them for new workloads and implementing end-to-end pipelines across Dev, QA, and Prod
Job Summary
Build and maintain SageMaker pipelines for embedding generation and NER workflows, extending them for new workloads and implementing end-to-end pipelines across Dev, QA, and Prod.
Deploy and optimize GPU instances for high-throughput inference workloads, implementing Spot Instance strategies and optimizing batch sizes, memory allocation, and concurrency.
Define standards for ML deployment and CI/CD pipelines, building deployment workflows and implementing automated health checks and alerting using AWS Lambda.
Matching Summary
Build and maintain SageMaker pipelines for embedding generation and NER workflows, extending them for new workloads and implementing end-to-end pipelines across Dev, QA, and Prod.
Skills & Requirements
Must-have
SageMaker Pipelines & Model Monitoring
GPU/CPU Performance & Cost Optimization
Search Infrastructure (Elasticsearch/Lucene)
ML Deployment & Platform Engineering
Production Deployment & Cloud Operations
PyTorch and TensorFlow models
AWS SageMaker expertise
Nice-to-have
CNNs, diffusion models, deep learning
Ranking systems (cross-encoder / bi-encoder)
Approximate Nearest Neighbors (HNSW)
Multimodal ML systems
Key Requirements
5+ years as ML Engineer or MLOps Engineer
Strong experience deploying PyTorch and TensorFlow models
Hands-on expertise with AWS SageMaker, Lambda, EC2
Proven experience with GPU/CPU optimization
Experience with Elasticsearch/Lucene
Expertise in containerized deployments and autoscaling
Strong understanding of feature engineering for BERT-based models