Join Our AI & GPU
Technology Team
We are building next-generation AI infrastructure and technologies focused on GPU Computing, AI Models, Model Optimization, and High-Performance AI Systems.
Our goal is to develop technologies that make AI models faster, more efficient, scalable, and cost-effective. We are looking for talented engineers and researchers who want to work at the intersection of AI models, GPU computing, distributed systems, and large-scale AI infrastructure.
Two roles. One AI stack.
One role goes deep into the models themselves; the other builds the GPU infrastructure they run on. Both work on the same question — how to make AI dramatically faster and cheaper to run.
AI Model R&D Engineer
Research, build, and optimize advanced AI models with a strong focus on GPU-based computing and model performance.
GPU & AI Systems Engineer
Design and build the GPU infrastructure, inference systems, and high-performance computing layer that AI models run on.
AI Model R&D Engineer
01Research, build, and optimize advanced AI models with a strong focus on GPU-based computing and model performance.
We are looking for an AI researcher/engineer who can investigate, develop, and optimize advanced AI models with a strong focus on GPU-based computing and model performance.
You will work on improving the efficiency and performance of AI models through model architecture research, fine-tuning, inference optimization, and GPU-aware model engineering.
The goal is not simply to use existing AI models, but to understand how models work, how they consume GPU resources, and how their performance can be significantly improved.
Key Responsibilities
15 items- 01Research and develop advanced AI/ML models
- 02Analyze and evaluate state-of-the-art AI architectures
- 03Optimize AI models for GPU-based execution
- 04Conduct model benchmarking and performance evaluation
- 05Research model efficiency and computational optimization
- 06Optimize model memory usage and GPU utilization
- 07Develop and evaluate model inference strategies
- 08Research model quantization, pruning, distillation, and compression
- 09Experiment with FP16, BF16, INT8, and other efficient computation methods
- 10Fine-tune and adapt AI models for specific workloads
- 11Analyze GPU memory consumption and computational bottlenecks
- 12Develop Proof-of-Concept implementations for new AI technologies
- 13Collaborate with GPU and systems engineers to optimize end-to-end AI workloads
- 14Evaluate emerging AI models and open-source AI technologies
- 15Turn research results into deployable AI technologies
Research Areas
The role may involve research across:
Send your CV and technical portfolio to info@aggx.io with “AI Model R&D Engineer” in the subject line.
Email your applicationQualifications
- Bachelor's degree or higher in Computer Science, AI, Machine Learning, Electrical Engineering, or a related field
- Strong understanding of machine learning and deep learning
- Strong Python programming skills
- Experience with PyTorch or other deep learning frameworks
- Understanding of neural network architectures and model training
- Strong interest in GPU computing and AI systems
- Ability to analyze technical papers and implement research ideas
- Strong problem-solving and analytical skills
Preferred Qualifications
Plus- Experience optimizing AI models for GPUs
- Experience with CUDA or GPU programming
- Experience with model quantization or compression
- Experience with distributed training or inference
- Experience with LLM / VLM / Transformer architectures
- Experience with TensorRT, ONNX, Triton, or similar technologies
- Experience with NVIDIA GPU platforms
- Research publications or strong AI research projects
- Experience profiling AI models and identifying computational bottlenecks
GPU & AI Systems Engineer
02Design and build the GPU infrastructure, inference systems, and high-performance computing layer that AI models run on.
We are looking for an engineer who specializes in GPU infrastructure, AI inference systems, and high-performance computing.
You will design and build the infrastructure that enables AI models to run efficiently across GPU environments.
The role focuses on the connection between AI models and GPU infrastructure, including GPU resource management, model serving, inference optimization, scheduling, scalability, and system performance.
Key Responsibilities
16 items- 01Design and develop GPU-based AI infrastructure
- 02Build high-performance AI inference systems
- 03Deploy and operate AI models across GPU environments
- 04Optimize GPU utilization and computational efficiency
- 05Develop GPU resource allocation and scheduling systems
- 06Optimize GPU memory and compute resource utilization
- 07Build scalable model-serving infrastructure
- 08Develop AI inference APIs and services
- 09Monitor GPU and AI workload performance
- 10Identify and resolve GPU utilization bottlenecks
- 11Optimize latency, throughput, and inference cost
- 12Develop distributed AI inference environments
- 13Automate AI model deployment and infrastructure operations
- 14Work with AI researchers to optimize models for production environments
- 15Benchmark GPUs, AI models, and inference frameworks
- 16Design systems for efficient multi-GPU workloads
Core Technology Areas
Send your CV and technical portfolio to info@aggx.io with “GPU & AI Systems Engineer” in the subject line.
Email your applicationQualifications
- Bachelor's degree or higher in Computer Science, Computer Engineering, AI, or a related field
- Strong programming skills in Python and/or C++
- Strong understanding of Linux systems
- Understanding of GPU computing and AI workloads
- Experience deploying AI/ML models
- Experience with Docker and containerized environments
- Understanding of backend systems and APIs
- Strong system troubleshooting and performance optimization skills
Preferred Qualifications
Plus- Hands-on experience with CUDA
- Experience with NVIDIA GPU infrastructure
- Experience with TensorRT or NVIDIA Triton
- Experience with Kubernetes
- Experience with multi-GPU systems
- Experience with distributed computing
- Experience with GPU virtualization or GPU partitioning
- Experience with GPU scheduling or resource management
- Experience optimizing AI inference latency and throughput
- Experience with profiling tools such as Nsight Systems or Nsight Compute
- Experience with large-scale AI infrastructure
- Experience with cloud GPU platforms such as AWS, Google Cloud, or Azure
Work across the entire AI stack
People who want to solve the fundamental
technical challenges behind modern AI
If you are interested in questions such as:
How can we run larger AI models with less GPU memory?
How can we increase GPU utilization?
How can we reduce AI inference latency and cost?
How can we efficiently distribute AI workloads across GPUs?
How can we build infrastructure capable of supporting large-scale AI workloads?
Then we would like to hear from you.
Send your application
to info@aggx.io
There is no online application form — we read every email directly. Write to us with the position you are interested in, and our engineering team will get back to you.
- Resume / CV
- Education, experience, and the technologies you have worked with hands-on.
- Position of interest
- AI Model R&D Engineer, GPU & AI Systems Engineer, or both.
- Technical portfolio
- GitHub, open-source contributions, projects, or benchmark work.
- Research (optional)
- Publications, preprints, or paper implementations you are proud of.
Build the AI Infrastructure of Tomorrow.