Brain-computer Interface Scientist

Noïa Labs; Paris; Sur place; EUR 120 000 - 180 000; Plein temps

Résumé du poste

Noïa Labs in Paris is seeking a talented BCI Scientist to lead neural decoding for our non‑invasive neural interface. You will identify brain-state markers stable across sessions and turn neuroscience insights into practical ML-ready approaches.

This hands-on role sits at the intersection of neuroscience and machine learning: design experiments, analyze neural and behavioral data, and own the decoding validation pipeline. Collaboration with ML and product teams is essential.

Qualifications

• 5+ years of experience in ML, computational neuroscience, or related fields.
• Experience building ML models for time-series data.
• Experience with neural or physiological signals (EEG/MEG/ECoG/EMG/ECG/eye tracking/PPG).
• Proficiency in Python and ML frameworks (PyTorch/JAX/TF).
• Strong signal processing, statistics, and experimental design background.
• Experience with personalization or transfer learning and online adaptation.
• Experience with real-time inference or low-latency ML systems.

Responsabilités

• Develop ML models for decoding neural and physiological time-series.
• Design benchmarks and ablations to evaluate performance and latency.
• Study model generalization across users, sessions, and contexts.
• Define labels and annotation protocols with data-collection teams.
• Collaborate with ML engineers to integrate methods into training/inference workflows.

Connaissances

Machine learning

Time-series ML

Python

PyTorch

JAX

TensorFlow

Signal processing

Experimental design

Online adaptation

Edge deployment

Description du poste

BCI Scientist - Neural Decoding

Paris, hybrid

Noïa Labs is an early‑stage neurotechnology company building the next generation of human‑AI interfaces.

We are working on one of the most ambitious problems in human‑AI interaction: creating a more natural way for people to control, guide, and collaborate with AI systems by relying directly on brain activity. Our approach combines optimized non‑invasive neural sensors with large‑scale AI models trained across many users to decode human intent from brain signals, without surgery.

Noïa Labs was founded by the team behind NextMind (acquired by Snap) and is backed by tier‑1 investors. We are at the beginning of the journey and are building a team of outstanding engineers and scientists where each person can have a major impact on the product and technology.

Role summary

We are seeking a talented BCI Scientist to lead the neural decoding efforts behind our non‑invasive neural interface. You will work on identifying the brain‑state markers that are stable, generalizable, and decodable at scale, and turning neuroscience insight into practical ML‑ready approaches.

This is a hands‑on scientific role at the intersection of neuroscience and machine learning: you will design experiments, analyze neural and behavioral data, and own the decoding validation pipeline. The role spans experimental design, signal analysis, decoding metrics, user studies, and collaboration with ML and product teams.

In this role, you will:

• Develop machine learning models for decoding neural and physiological time‑series
• Design experiments, benchmarks, and ablations to evaluate performance, robustness, latency, and generalisation.
• Study how models adapt across users, sessions, tasks, sensors, and contexts
• Work with data‑collection teams to define labels, tasks, and annotation protocols for training‑ready neural data
• Collaborate with ML engineers to turn promising methods into reliable training and inference workflows

For this role, you must:

• 5+ years of experience in ML, computational neuroscience, or a related field.
• Experience building ML or deep‑learning models for time‑series data
• Experience with neural or physiological signals such as EEG, MEG, ECoG, EMG, ECG, eye tracking, PPG, or related modalities
• Strong experience with Python and modern ML frameworks such as PyTorch, JAX, or TensorFlow
• Strong understanding of signal processing, statistics, model evaluation, and experimental design
• Experience with personalization, domain adaptation, transfer learning, few‑shot learning, or online adaptation
• Experience with real‑time inference, edge deployment, or low‑latency ML systems