Hands-on ML Inference Deployment Engineer

Socket.dev is seeking a Forward Deployment Engineer to work directly with customers to design, deploy, and validate Inference dedicated endpoints and MaaS products on GMI’s global infrastructure. This hybrid role sits at the intersection of platform engineering, applied ML, and customer success, embedding with customers during early-stage deployments to turn research ideas into performant systems on real GPU clusters. #J-18808-Ljbffr