Solutions Architect with GPU infrastructure

Job Description

Role: Lead Solution Architect

\n

Location: Remote

\n

Contract Position .

\n

Key Performance Indicators

\n

· Technical win rate and contribution to closed contract value on strategic US GPUaaS pursuits

\n

· Size and complexity of deals shaped (committed capacity, multi-year value)

\n

· Accuracy of sizing versus delivered performance and cost, and quality of delivery outcomes

\n

· Team adoption of reference architectures, sizing tools and benchmark standards

\n

· Partner standing with NVIDIA and AMD, thought leadership output, and growth of architects mentored

\n

Required Experience

\n

· 15+ years in enterprise infrastructure, cloud or solution architecture, including customer-facing pre-sales or consulting roles.

\n

· GPU infrastructure (mandatory): 5+ years hands-on designing, deploying or operating GPU clusters.

\n

· GPU selling: 1+ years selling GPU capacity, GPU cloud or AI infrastructure, with technical wins on multi-year GPU commitments.

\n

· AI data center: Understanding of AI data center nuances (high-density power, liquid cooling, power availability and lead times, facility readiness) and how they constrain GPU design, cost and timelines.

\n

· Scaling AI workloads: Experience scaling production AI workloads from single node to multi-node and multi-cluster, including autoscaling, multi-tenant GPU sharing and capacity planning.

\n

· LLM inference: 2+ years deploying and operating LLM inference in production (such as vLLM, SGLang, TensorRT-LLM or NIM).

\n

· Hands-on coding: Strong, current hands-on coding in Python, plus Bash and Infrastructure as Code (Terraform, Ansible, Helm). Personally builds POCs, benchmark harnesses, sizing tools and inference deployments, not only designs them.

\n

· Hands-on technical skills: Personally deploys and troubleshoots GPU environments: Linux administration, GPU drivers and CUDA/ROCm, containers, Kubernetes (GPU Operator, Helm), standing up and tuning serving engines (vLLM, SGLang), running benchmarks (GenAI-Perf, NCCL tests) and monitoring (DCGM, Prometheus, Grafana).

\n

· Technical Expertise

\n

· GPU infrastructure

\n

· Accelerators and their sizing characteristics (HBM, memory bandwidth, scale-up domain, power): NVIDIA H100/H200, B200/B300, GB200/GB300 NVL72; AMD Instinct MI300X/MI325X/MI355X ; roadmap awareness (Vera Rubin, MI400).

\n

· Networking and storage: NVLink/NVSwitch, InfiniBand and RoCEv2/Spectrum-X, SuperNICs/DPUs; parallel and all-flash file systems (WEKA, VAST, DDN) and GPUDirect Storage.

\n

· Orchestration and multi-tenancy: Kubernetes with NVIDIA GPU Operator and AMD ROCm equivalents, MIG, time-slicing, bare-metal provisioning on OpenStack, tenant isolation and quotas.

\n

· Data center and validation: 40 kW to 140 kW+ racks, direct-to-chip liquid cooling, burn-in and acceptance testing (DCGM, NCCL/RCCL), NVIDIA and AMD reference architectures.

\n

· Inference

\n

· Serving engines: vLLM, SGLang, TensorRT-LLM, Triton and NIM, AMD ROCm stack; KServe and Gateway API Inference Extension; disaggregated serving (NVIDIA Dynamo, llm-d).

\n

· Optimization: continuous batching, KV-cache management, prefix caching, speculative decoding and quantization (FP8, FP4, INT4).

\n

· Sizing and benchmarking: GPU count, type and parallelism (tensor, pipeline, expert) to model, context length, traffic and SLA; TTFT, inter-token latency, goodput and cost per million tokens.

\n

\n

· Open-weight models (Llama, Qwen, DeepSeek, Mistral, gpt-oss), including MoE and long-context models, plus RAG, agentic and model-gateway patterns.

\n

\n

\n

Thank you,

\n

\n

Bharath M

\n

Account Manager