AI Runtime Engineer

About the role

EnCharge AI is looking for an AI Runtime Engineer to build and optimise the software stack that runs deep‑learning models on its next‑generation AI accelerator. You will work on low‑latency, high‑performance runtime components that bridge hardware, compilers and AI frameworks for both cloud and edge deployments.

Key responsibilities

• Develop and optimise the AI runtime software stack for executing deep‑learning workloads on AI accelerators.
• Implement task scheduling, memory management and kernel execution strategies for efficient computation.
• Optimise data movement between host and device using PCIe, DMA and shared memory.
• Design high‑performance APIs for inference frameworks such as OpenVINO, ONNX Runtime and vLLM.
• Perform graph execution optimisations including kernel fusion, pipelining, tensor tiling and caching.
• Integrate runtime components with AI compilers (LLVM, MLIR, XLA, TVM) to achieve optimal execution.
• Ensure scalability and reliability of the runtime for cloud‑based and edge AI deployments.

Required profile

• Bachelor’s or Master’s degree in Computer Science, Electrical Engineering or a related field.
• 3+ years of experience developing low‑level runtime software for AI accelerators, GPUs or HPC systems.
• Strong proficiency in C/C++ and low‑level systems programming.
• Deep understanding of task scheduling, concurrency and memory hierarchy.

Required skills

• Low‑level programming in C/C++.
• Task scheduling, concurrency and memory‑hierarchy optimisation.
• PCIe, DMA and shared‑memory data‑movement techniques.
• Experience with AI inference frameworks such as OpenVINO, ONNX Runtime, TVM, TensorRT.
• Familiarity with compiler infrastructures like LLVM, MLIR, XLA.
• Debugging and profiling tools for AI performance tuning.
• Knowledge of AI model deployment pipelines (Triton, TensorFlow Serving).