Senior GenAI Platform Engineer

About the job 🚀 We're Hiring | Gen AI Platform Engineer (5–8 Years) Are you passionate about building enterprise-scale Generative AI platforms? We're looking for a Gen AI Platform Engineer to design, deploy, and manage production-grade LLM platforms with cutting-edge AI infrastructure. 📍 Location: PAN India 💼 Experience: 5–8 Years 📄 Employment Type: Contract / Full-Time 🔹 Key Skills ✅ Python ✅ LLMOps (vLLM, LiteLLM) ✅ Kubernetes / OpenShift ✅ GPU Infrastructure (CUDA, Tensor Parallelism, KV Cache) ✅ LLM Deployment & Model Serving ✅ LoRA / QLoRA / PEFT ✅ Quantization (AWQ, GPTQ, GGUF) ✅ Prompt Engineering & Model Evaluation ✅ AI Security (NeMo Guardrails, OWASP LLM Top 10, PII Protection, AI Red Teaming) ⭐ Good to Have • NVIDIA AI Enterprise • TensorRT-LLM • Hugging Face • LangChain / LangGraph • RAG & Vector Databases • Prometheus & Grafana • Argo CD / Helm (GitOps) • DeepSpeed / FSDP • SAP Integrations If you have experience building scalable, secure, and high-performance AI platforms, we'd love to connect! 📩 Interested candidates can reach out via DM or share their updated resume at hr@runmapglobal.com.