Machine Learning Engineer

• Deploy scalable, production-ready ML services with optimized infrastructure and auto-scaling Kubernetes clusters
• Optimize GPU resources using MIG (Multi-Instance GPU) and NOS (Node Offloading System)
• Manage cloud storage such as S3 for high availability and performance
• Integrate LoRA and model merging workflows into ML processes
• Work with and adapt state-of-the-art ML codebases to organizational needs
• Deploy and manage LLMs, SLMs, and LMMs
• Serve ML models using Triton Inference Server
• Use vLLM, TGI, and other state-of-the-art serving frameworks
• Optimize models with ONNX and TensorRT
• Develop RAG systems integrating spreadsheet, math, and compiler processors
• Set up monitoring and logging using Grafana, Prometheus, Loki, Elasticsearch, and OpenSearch
• Write and maintain CI/CD pipelines using GitHub Actions
• Create Helm templates for rapid Kubernetes node deployment
• Automate workflows using cron jobs and Airflow DAGs

Explore Senior MLOps Engineer at Fortytwo. Review requirements and application details.