ML Engineer - Life Sciences (Early Talent)
Core
Optimizing inference speed and efficiency for large biological AI models (protein folding/design) to enable real-world research and production use.
Role type
ML Engineer (Inference Optimization)
Builds
Efficient inference pipelines for biological foundation models
Domain
Life Sciences / AI Infrastructure
Deliverable
production ML models
Required skills
Python, deep learning frameworks, model compression (quantization, pruning, distillation), profiling, clean code
Preferred skills
Large language models, transformer architectures, GPU workload optimization, distributed inference, open-source contributions
Technologies
Python, deep learning frameworks, GPU
Responsibilities
Profile inference bottlenecks in biological models, implement optimization techniques, explore architecture-level improvements, build and benchmark optimized pipelines, evaluate speed/memory/accuracy trade-offs, write documented code, share deployment recommendations
Seniority
Early Career / Student