Middle AI Engineer (Inference Engineering)

Type: Full- time
Location: Ho Chi Minh City, Vietnam
Team: AI / Engineering
AI Engineer
About Autonomous
We are building intelligent products that combine hardware, software, and AI to enhance how people work, create, and interact
with technology in real life.
Our mission is to build AI- powered systems and products that enhance human productivity and creativity at scale.
product company.
Autonomous is an AI- native company founded in 2015, transforming from smart office products into a global AI hardware and
About the Role
someone strong in model development, inference optimization, and production deployment, with the ability to work across
research, engineering, and product teams.
We are looking for an AI Engineer to help build, optimize, and deploy AI systems for real- world products. This role is ideal for
What You’ll Work On
You will work across Autonomous’ key AI product ecosystem, with a focus on:
Workspace AI: AI features for Autonomous’ workspace products, including desks, chairs, and WorkPods, making them more
intelligent, adaptive, and personalized.
Lamp: A physical AI companion for your desk that sees, hears, remembers, and proactively checks in before you ask,
powered by expressive motion and local AI for private, personal interactions.
Intern: The world’s first personal AI device, powered by OpenClaw, designed to handle tasks through simple text
instructions: “Text it. It’s handled.
”
You will help build AI capabilities that turn user requests into real actions across work, research, and productivity workflows.
Responsibilities

Develop, train, evaluate, and optimize AI/ML models for production use cases.
Build and improve inference pipelines for computer vision, LLM, and multimodal AI systems.
Optimize model performance, latency, and cost using techniques such as quantization, pruning, ONNX, TensorRT, or Triton Inference Server.
Stay updated with new AI models, frameworks, and optimization techniques.
Deploy AI models into production environments and monitor performance over time.
Review code, improve model- serving workflows, and contribute to engineering best practices.
Conduct experiments, benchmark models, and document technical findings clearly.
Work with engineering teams to integrate AI models into applications, services, or device- side systems.

Requirements

2+ years of hands- on experience in AI/ML engineering, deep learning, or applied AI.
Good problem- solving skills and willingness to work in a fast- paced product environment.
Strong programming skills in Python.
Familiarity with model optimization or inference deployment.
Experience with PyTorch or TensorFlow.
Solid understanding of machine learning, deep learning, model evaluation, and data preprocessing.
Experience building or deploying AI models in real- world projects.
Ability to read technical papers, experiment with new models, and turn research into working systems.

Nice to Have

Experience with edge deployment, Jetson, embedded systems, or device- side AI.
Experience with ONNX, TensorRT, Triton Inference Server, vLLM, llama.cpp, or similar inference tools.
C/C++ experience.
Experience with computer vision, LLMs, RAG, multimodal systems, or AI agents.
Strong math foundation or research background.
Experience with Docker, cloud deployment, CI/CD, or production ML pipelines.

What We Look For

Strong technical foundation and curiosity.
Ability to learn fast and ship practical AI systems.
Interest in building AI products from Vietnam for the global market.
Hands- on builder mindset.
Clear communication and ownership.

Cập nhật gần nhất lúc: 2026-07-06 22:00:04