【Research Engineer, LLM/Agent】Japanese N2/global friendly working environment

Sourced from jp.linkedin.com

Join G Talent as a Research Engineer focused on cutting-edge LLM and AI agent development. You will work on agent harness design, benchmarking, and production integration in a hybrid environment based in Tokyo. The company leverages AI to enhance enterprise productivity and requires Japanese N2 level.

• Conceive, develop, and compare different agent harnesses (memory, context compression, inter-agent communication architectures, etc.)
• Research and develop new reasoning, planning, and retrieval methods
• Develop technologies for multimodal and long-context handling
• Design and implement rigorous quantitative benchmarks for large-scale agentic tasks
• Support automated evaluation of models and prompts across the full lifecycle
• Optimize inference latency and cost (quantization, distillation, caching, etc.)
• Create and optimize training data mixes
• Transfer technology and mentor the Agentic Product Engineer team

• Master's or Ph.D. in Computer Science, AI, ML, or related field
• Experience developing complex agentic systems using LLMs
• Significant hands-on experience in software engineering and ML
• Experience with LLM prompt engineering and building products with language models
• Experience with large-scale model training and inference using PyTorch or JAX
• Deep understanding of LLM and Transformer architectures
• Ability to read, reproduce, and improve upon research papers
• Strong implementation skills in Python
• Language: Japanese N2 level or Business English

• Experience with TypeScript, React, Next.js
• Familiarity with GCP, Docker, Kubernetes