Member of Technical Staff, NeuroAI

pNeurosoft Bioelectronics is developing next-generation AI for decoding neural time series (high-density subdural ECoG LFPs). We seek an intern machine learning scientist with expertise in sequence modelling, state-space methods, self-supervised learning, and/or physics-informed machine learning to build foundation models that infer dexterous finger movements and continuous high DoF upper extremity kinematics, initially from only few minutes of brain data. The role spans modern system identification, representation learning, and real-time deployment of low-latency inference pipelines. /p h2Tasks /h2 ul liDesign and benchmark Kalman filters, RNNs, LSTMs, Structured State Space Models (S4/S5), Mamba, Neural ODEs, and related sequence architectures. /li liDevelop large-scale self-supervised pretraining pipelines and subject-specific fine-tuning workflows. /li liReproduce and extend published SoTA neural decoding methods, beginning with LSTM baselines and modern SSM architectures. /li liDecode individual fingers, grasp synergies, continuous gestures, and full 6 DoF hand pose. /li liDeploy streaming inference using ONNX, TensorRT, Triton, and GPU acceleration. /li liMaintain reproducible benchmarking, MLOps, and production research infrastructure. /li /ul h2Requirements /h2 ul liTheoretical foundations of time-series modelling, system identification, dynamical systems, differential equations, control theory, and Bayesian estimation. /li liRecent implementaiton of Kalman filters, HMMs, linear/nonlinear SSMs, RNNs, LSTMs, S4/S5, Mamba, Neural ODEs, or Transformer-based sequence models. /li liAny experience with contrastive learning, VAEs, foundation-model pretraining, transfer learning, domain adaptation, and few-shot learning. /li liOptional: Profficiency in Python, PyTorch, CUDA, Docker, ONNX, TensorRT, Triton, Git, Linux, and MLflow. /li /ul h2Benefits /h2 ul listrongGrowth: /strong Opportunity to join an ambitious neurotechnology startup with exposure to multiple areas of company operations. /li listrongCulture: /strong A collaborative and dynamic team environment with direct interaction with founders and leadership. /li listrongFlexibility: /strong Hybrid work model with the possibility remotely and at the office in Geneva. /li listrongCompensation: /strong Entry-level salary range of strong45'000 - 55’000 CHF /strong per year. First promotional review after 3 months. /li listrongOwnership: /strong Equity participation through the employee option plan may be available. /li /ul pWe view neural decoding as a problem of system identification: learning latent state-space representations that increasingly approximate the underlying continuous dynamical system generating voluntary movement of a particular individual. Your role is about implementing, testing, and benchmarking the methods developed in collaboration with our academic partners. /p pDue to the novelty of this effort, this is a mandatory intake role across all seniority levels. At any point you take over an essential practice, tech stack, or reach an essential milestone, your compensation and authority will reflect that. Your role scope and growth are entirely metrics-driven and evaluated quarterly. This is a CSO-track role. /pbrpAt Neurosoft Bioelectronics we strive toward revolutionizing the way we interface with neural tissue, allowing the development of breakthrough therapies which would not be possible with outdated clinical technology. /p pAt our core, we are committed to the design and development of better interfaces for the brain and beyond, with the aim of significantly improving the treatment of severe neurological disorders, such as epilepsy, tinnitus and deafness. /p