DevOps Inference Engineer

Synergyassure Inc is seeking a Senior DevOps / Inference Engineer to build and optimize large-scale AI infrastructure supporting self-hosted and API-based LLMs. The role involves designing scalable GPU environments and optimizing inference performance while managing model serving platforms and improving reliability.

Responsibilities:

• Designing scalable GPU environments
• Optimizing inference performance
• Automating infrastructure
• Managing model serving platforms
• Improving reliability
• Reducing cloud costs

Requirements:

• strong expertise in model inference
• GPU infrastructure
• AWS cloud services
• Terraform
• Kubernetes/ECS
• production-grade DevOps practices
• designing scalable GPU environments
• optimizing inference performance
• automating infrastructure
• managing model serving platforms
• improving reliability
• reducing cloud costs
• AWS (EKS, ECS, EC2 GPU Instances, IAM, VPC, KMS, ECR, CloudWatch)
• Terraform (Infrastructure as Code)
• LLM Inference & Model Serving (Mandatory)
• GPU Infrastructure & CUDA Workloads
• Kubernetes / ECS Container Orchestration
• Model Serving Frameworks (vLLM, Triton, TensorRT-LLM, Ollama, etc.)
• Inference Optimization (Batching, Quantization, KV Cache, Multi-GPU Sharding)
• CI/CD Automation
• Docker & Containerization
• Cloud Cost Optimization
• Monitoring & Observability
• Python (Preferred)
• AWS Bedrock / SageMaker (Preferred)
• Healthcare AI Experience (Nice to Have)