AI Inference & Quantization Engineer

present of AI; Greater London; Ibrido; GBP 85.000 - 120.000; Tempo pieno

Descrizione del lavoro

Lamb Labs is seeking a Member of Technical Staff focused on Model Quantization & Inference. The role emphasizes Python and deep learning workflows, quantization, and hardware-aware optimization to accelerate inference on custom silicon.

The candidate will benchmark accuracy and latency, reproduce quantization results on open models, and ensure numerical stability under hardware constraints. Collaboration with hardware teams is expected.

Competenze

• Solid Python and deep learning framework experience.
• Experience with quantization and inference optimization.
• Ability to benchmark and assess tradeoffs between speed, size and quality.
• Experience aligning models with hardware constraints.

Mansioni

• Shrink models through quantization and optimize for fast inference.
• Evaluate numerical accuracy and track tradeoffs between speed, size and quality.
• Explain tradeoffs and ensure alignment with hardware constraints.

Conoscenze

Python

Benchmarking

Numerical accuracy

Hardware-aware optimization

Strumenti

PyTorch

Descrizione del lavoro

Lamb Labs is seeking a Member of Technical Staff focused on Model Quantization & Inference. The role emphasizes Python and deep learning workflows, quantization, and hardware-aware optimization to accelerate inference on custom silicon.

The candidate will benchmark accuracy and latency, reproduce quantization results on open models, and ensure numerical stability under hardware constraints. Collaboration with hardware teams is expected.