Model Optimization Engineer
New
B
Bright Vision TechnologiesAI systems
100% Remote (U.S.)Full-TimeSenior
Salary150,000 - 175,000 USD per year
Apply NowOpens the employer's application page
Job Details
- Experience
- Six or more years of experience in performance engineering, ML systems, or HPC.
- Required Skills
- PythonC++
Requirements
- Hold a Bachelor’s or Master’s degree in Computer Science, Computer Engineering, or a related field.
- Have six or more years of experience in performance engineering, ML systems, or HPC.
- Demonstrate strong proficiency in Python and C++.
- Have hands-on experience optimizing deep learning workloads on modern GPUs.
- Understand distributed training and inference techniques.
- Have experience with profiling tools across CPU, GPU, and distributed systems.
- Be familiar with model compression techniques and their accuracy implications.
- Understand memory hierarchies, communication primitives, and parallelism strategies.
- Bring measurement, debugging, and analytical reasoning skills.
- Have experience optimizing LLM inference at production scale (preferred).
- Have contributions to vLLM, TensorRT-LLM, DeepSpeed, or similar projects (preferred).
- Be familiar with custom kernel authoring in Triton or CUTLASS (preferred).
Responsibilities
- Optimize throughput, latency, and cost across training and inference workloads for large neural network systems.
- Optimize low-level kernels and tune distributed systems.
- Apply GPU architecture, model parallelism, memory management, and compiler-level optimization.
- Instrument and measure production AI workloads to guide optimization decisions.
- Translate ambiguous requirements into well-engineered solutions with cross-functional partners.
- Participate in code reviews and design reviews.
- Mentor more junior engineers.
View Full Description & ApplyYou'll be redirected to the employer's site
