Technical Support Engineer
Core
Provide enterprise-level technical support and troubleshooting for GenAI inference platforms, focusing on MLOps, model deployment, and infrastructure issues.
Role type
Senior IC Technical Support Engineer (MLOps)
Builds
GenAI inference platforms (LLMs, speech, vision, diffusion) for enterprise clients
Domain
Generative AI, MLOps, Cloud Infrastructure
Deliverable
client delivery
Required skills
Kubernetes troubleshooting, Linux, Python, SQL, cloud platforms (AWS/GCP/Azure), observability tooling (Prometheus/Grafana), ML frameworks (TensorFlow/PyTorch), inference engines (vLLM/TensorRT-LLM/Triton)
Preferred skills
Helm, Docker, NVIDIA GPUs/CUDA, SAAS experience, additional ML/cloud certifications
Technologies
Kubernetes, Linux, Python, SQL, AWS, GCP, Azure, Prometheus, Grafana, Freshdesk, Jira, TensorFlow, PyTorch, vLLM, TensorRT-LLM, Triton Inference Server, Docker, NVIDIA CUDA
Responsibilities
Diagnose and troubleshoot ML model, framework, and deployment pipeline issues; assist with network configuration affecting ML performance; document MLOps best practices and troubleshooting steps; escalate unresolved issues to data science or development teams; follow up with clients to confirm system functionality post-troubleshooting.
Seniority
Mid-level, hands-on IC
