Description
Responsibilities: Design realistic technical scenarios involving LLM inference optimization, GPU kernel development, and systems performance engineering. Develop reference solutions and detailed technical explanations for challenging engineering problems Evaluate AI-generated solutions for correctness, efficiency, and technical depth. Assess approaches to GPU performance optimization and model-serving architecture.
Identify errors in technical reasoning, implementation strategies, and performance recommendations. Provide structured feedback to improve AI model capabilities. Document evaluation criteria and explain the reasoning behind technical assessments.
Requirements
Bachelor's degree or higher in Computer Science, Computer Engineering, Electrical Engineering, or a related field. Strong hands-on experience in one or more of the following areas: GPU inference optimization Custom CUDA kernel development LLM inference and model-serving systems Quantization techniques Optimizer design Systems performance engineering Familiarity with model-serving frameworks such as vLLM, TensorRT-LLM, or SGLang. Experience working at a recognized technology or AI company in a role involving practical systems-engineering responsibilities.
Strong analytical and problem-solving skills. Excellent written communication skills, including the ability to explain complex technical concepts clearly. Remuneration: NGN 550,000
Company and the link to apply — after you sign in.
Sign inEmployer contacts (email/phone/telegram) are hidden from the public preview.
Send your CV so employers can reach you directly.