This is a fully remote position, open to applicants in Poland.

• Engage in the deployment of machine learning models on edge devices utilizing the frameworks: llama.cpp and ggml.

• Work closely with researchers to aid in coding, training, and transitioning models from research settings to production environments.

• Incorporate AI features into current products, enhancing them with the latest advancements in machine learning.

• Proficient programming skills in C++, with additional experience in Javascript being advantageous.

• Strong familiarity with Llama.cpp and ggml inference engines, enabling the deployment of models to particular GPU architectures.

• Solid understanding of deep learning principles and model architectures.

• Experience with transformers, LLMs, and Diffusion models.

• Proven ability to swiftly learn new technologies and methodologies.

• A degree in Computer Science, AI, Machine Learning, or a related discipline, accompanied by a robust background in AI research and development.

• Remote flexibility: Work in the environment and manner that suits you best - we trust you to deliver results.

• Fair compensation: Competitive salary along with meaningful benefits (medical, educational).

• Ownership opportunities: Identify a challenge worth addressing? Take charge. We support intelligent risks over bureaucratic caution.

• AI enhancement: We utilize AI to enhance your efficiency and effectiveness - augmenting your skills, not substituting them.

• Learning investment: English classes and opportunities for professional development.

• Career progression: Clear pathways for advancement, not merely lateral moves.

• Responsive teammates: No ignored messages, no "not my problem" attitudes.

• Supportive culture: When you encounter challenges, colleagues are ready to assist. When issues arise, we resolve them together.

• Human connections: Regular meetups, tech discussions, and genuine relationships beyond the workplace.

AI Inference Engineer – QVAC

People also viewed