Point your AI agent at freehire and let it find you a job. A CLI and an MCP server over the whole job API — no browser.
Role Summary Firmus Technologies is seeking an experienced AI Engineer to design, develop, implement and maintain the MLOps and AIOps foundations for Firmus AI Factory, our AI platform, to make it trustworthy,…
Senior AI engineer building and running Firmus's self-hosted AI model inference platform on its GPU cloud — onboarding models, provisioning secure scalable endpoints, optimizing LLM serving performance (quantization, batching, parallelism), and benchmarking runtimes like TensorRT-LLM, vLLM, and Triton on NVIDIA CUDA/Kubernetes infrastructure.
Designs, builds, and operates production-grade agentic AI applications that automate and optimize AI-factory operations across Firmus's Model-to-Grid platform. Day to day: building LLM agent orchestration, RAG pipelines, and tool integrations using Python, agent frameworks like LangGraph/LangChain, vector databases, and Kubernetes-based observability and evaluation tooling.
Designs, builds, and operates a proprietary Kubernetes-native job scheduler that orchestrates training, fine-tuning, inference, batch, and agentic workloads across massive-scale GPU AI factories. The role is heavy on Go-based Kubernetes controller/scheduler engineering, topology-aware GPU placement (NVLink/NVSwitch, RDMA), and observability.
We couldn't check your fit for this role — add a CV to your profile to see it next time.