← Back to jobs
Job Description
Top 3 Reasons To Join Us
Môi trường đẩy nhanh phát triển năng lực
Nơi quy tụ nhân tài người Việt trên toàn cầu
Văn hóa thành công, đề cao sáng kiến
The Job
We are seeking a high-caliber Senior AI System Engineer to lead the development and optimization of production-grade AI systems. You will focus on scaling Generative AI applications and maximizing hardware efficiency. The ideal candidate has deep expertise in high-performance serving frameworks and low-level GPU programming to bridge the gap between cutting-edge research and scalable industrial products.
Work Location: HCM or HN
Level: Middle/Senior/Expert
KEY RESPONSIBILITIES
- High-Performance Serving: Architect and deploy LLM/VLM serving infrastructures using vLLM, SGLang, or Triton Inference Server.
- GPU & Inference Optimization: Optimize model latency and throughput via CUDA programming, custom GPU kernels, and quantization techniques (FP8 / FP4).
- GenAI Productionization: Build and scale end-to-end Generative AI workflows, including; can translate business requirements into AI workloads, and understand what AI can and cannot do.
- System Architecture: Design microservices-based AI architectures using FastAPI, gRPC, and/or Kubernetes to handle large-scale traffic and data.
- Performance Engineering: understand how to debug slow systems, such as via profiling techniques.
- MLOps Leadership: Lead the implementation of automated pipelines for model retraining, evaluation, and deployment using Kubeflow or similar platforms.
- Education: We don’t care about your degree, so long as you can prove your knowledge and value.
- Core Programming: Mastery of Python and C++ (specifically for parallel programming and system optimization).
- AI Serving Stack: Experience with vLLM, SGLang, and/or NVIDIA TensorRT.
- Experience: 3+ years of experience (or equivalence) building production AI systems.
Preferred Skills (Nice to Have)
- GPU Expertise: Direct experience with CUDA, CUTLASS, CuTe DSL, or AMD ROCm HIP for deep learning pipeline execution.
- Deployment: Strong proficiency in Docker, Kubernetes, and cloud environments (AWS/GCP).
Salary & Allowances
- 13-month salary with annual performance bonus, project incentives, sales incentives (based on position)
- Lunch allowance: 730.000 VND/month
- Special occasion bonus: 3.000.000 - 5.000.000 VND/year
- Annual leaves: Up to 20 days/year (based on levels)
- Health: Social insurance, premium health insurance, yearly health check
- Laptop, screen and other needed facilities/ accounts/ tools for work
Career Growth
- Yearly salary review and promotion
- Diverse career path: Management or Expert and functions rotation opportunity
- Free learning sources in Udemy, Coursera, O'relly platforms; internal workshop, certification sponsorship, and exclusive mentoring from C-levels
- Recognition and awards at team and organizational levels.
Working Environment
- Open & collaborative working space foster both individual focus and teamwork activities
- Young, dynamic, and collaborative working atmosphere
- Unwind zones: gaming, table tennis, yoga, gyms, bath rooms, sleep corner.
- Quarterly/yearly teambuilding & engaged internal events.
Benefits
Salary & Allowances
- 13-month salary with annual performance bonus, project incentives, sales incentives (based on position)
- Lunch allowance: 730.000 VND/month
- Special occasion bonus: 3.000.000 - 5.000.000 VND/year
- Annual leaves: Up to 20 days/year (based on levels)
- Health: Social insurance, premium health insurance, yearly health check
- Laptop, screen and other needed facilities/ accounts/ tools for work
Career Growth
- Yearly salary review and promotion
- Diverse career path: Management or Expert and functions rotation opportunity
- Free learning sources in Udemy, Coursera, O'relly platforms; internal workshop, certification sponsorship, and exclusive mentoring from C-levels
- Recognition and awards at team and organizational levels.
Working Environment
- Open & collaborative working space foster both individual focus and teamwork activities
- Young, dynamic, and collaborative working atmosphere
- Unwind zones: gaming, table tennis, yoga, gyms, bath rooms, sleep corner.
- Quarterly/yearly teambuilding & engaged internal events.