Job Responsibilities:

1. Design, train, evaluate, deploy, and maintain computer vision algorithms for energy asset inspection, including defect detection, object detection, semantic segmentation, and anomaly detection.

2. Lead the selection of large language model (LLM) technologies and optimize model inference performance (e.g. model compression, distillation, quantization), driving engineering deployment to support enterprise-level intelligent applications.

3. Based on business requirements, design and implement LLM-based solutions such as RAG, semantic search, intelligent Q&A systems, and Agents, delivering end-to-end applications.

4. Cross-functional engineering delivery: collaborate with product, frontend, backend, and operations teams to integrate algorithms with systems, support on-site deployment, and ensure stable and successful project delivery.

5. Technical accumulation and capability replication: reproduce and summarize key papers and methods, prepare technical documentation, and promote knowledge sharing and reuse.

Job Requirements:

1. Bachelor’s degree or above in Computer Science, Mathematics, Artificial Intelligence, or related fields; Master’s degree preferred.

2. At least 3 years of experience in algorithm engineering or related roles, with proven experience in industry-level project delivery; candidates with a background in energy asset inspection or manufacturing are preferred.

3. Proficient in Python, with strong hands-on experience using deep learning frameworks such as PyTorch or TensorFlow, and solid algorithm implementation and optimization skills.

4. Solid understanding of LLM principles and applications, including the Transformer architecture; experience with RAG, semantic search, model fine-tuning (LoRA / PEFT), or Agent-based applications is a strong plus.

5. Strong communication skills and team collaboration mindset, with the ability to translate technical solutions into executable engineering tasks; ability to read and understand English technical materials is a plus.