2 months ago
Tokyo, JapanSenior
Responsibilities
- Own applied ML projects for customers in Japan from discovery and scoping through production deployment.
- Integrate, profile, and optimize model inference for latency, throughput, memory, power, cost, and reliability requirements.
- Build data pipelines, evaluation systems, serving components, and reference implementations around models.
- Fine-tune or post-train models using supervised fine-tuning, parameter-efficient fine-tuning, and preference optimization when needed.
- Design task-specific evaluations, conduct error analysis, and iterate across data, models, inference, and system design.
- Work directly with customer engineering teams during design, integration, testing, and rollout, including occasional on-site work.
- Convert deployment lessons into reusable tooling and feedback for models, inference infrastructure, documentation, and product planning.
Requirements
- Strong engineering skills and experience building, testing, and shipping production-quality ML systems.
- Hands-on experience deploying modern language models, multimodal models, or other deep learning systems beyond a notebook or API proof of concept.
- Experience with model serving, performance profiling, or inference optimization, including balancing model quality with system constraints.
- Proficiency with the open-source ML ecosystem.
- Experience designing evaluations, analyzing model failures, and driving measurable improvements.
- Ability to lead technical discussions with customers and translate ambiguous requirements into shipped systems.
- Professional proficiency in English for complex technical collaboration with global teams.
- Experience leveraging agents to amplify personal work.
- Working proficiency in Japanese is preferred.
- Experience with LLM post-training methods is preferred.
- Experience with inference and deployment frameworks such as vLLM, SGLang, llama.cpp, ONNX Runtime, or MLX is preferred.
- Familiarity with quantization, hardware-aware optimization, or deployment on mobile, embedded, automotive, or other edge platforms is preferred.
- Experience with multimodal systems involving text, vision, audio, or sensor data is preferred.
- Experience delivering ML systems for enterprise or regulated environments is preferred.
- Degrees and publications are not required.
Benefits
- Primarily remote for candidates based in Japan, with Tokyo office attendance once or twice weekly.
- Fully flexible working hours.
- Travel to the United States, relevant conferences, and occasionally within Japan for customer work.
- Unlimited paid time off.
- Equity and standard employee benefits in Japan.
Categories
ML EngineeringSolutions Engineering
About Liquid AI
Liquid AI builds general-purpose AI systems that run efficiently from data center accelerators to on-device hardware, emphasizing low latency, memory efficiency, privacy, and reliability. The company partners with enterprises in consumer electronics, automotive, life sciences, and financial services to deploy and benchmark models for real-world workloads. Founded in 2023 out of MIT CSAIL and headquartered in Cambridge, Massachusetts, it is privately held.