
Cellcraft is a biotechnology company pioneering the production of cultivated meat through revolutionary technology. Their end-to-end process, inspired by nature, allows for the cultivation of real…

Cellcraft is a biotechnology company pioneering the production of cultivated meat through revolutionary technology. Their end-to-end process, inspired by nature, allows for the cultivation of real…
Cellcraft is a B2B biotechnology startup building intelligent infrastructure for biomanufacturing. Our flagship platform, Cellcraft IQ, applies machine learning and real-time control to bioreactors, enabling adaptive optimisation, predictive monitoring and autonomous process tuning. We are transforming bioprocessing into a data-driven engineering discipline that supports reliable, scalable production across biopharma and cultivated meat.
Tasks
Lead integration of Cellcraft IQ at customer sites, connecting to bioreactor systems via Modbus TCP, OPC UA, and PROFINET
Design data pipelines for acquisition, cleaning and structuring of high-frequency
sensor and process data
Integrate ML models with embedded controllers and supervisory control systems
Contribute to software architecture for scalable deployment of control and analytics
systems
Work directly with customer technical teams to scope, configure, and validate deployments
Collaborate closely with Cellcraft's senior integration engineer (UK-based) throughout each deployment
Troubleshoot integration issues across diverse bioreactor OEM environments
Document configurations, integration steps, and site-specific setups for each customer
Act as the primary technical point of contact for customers during and after onboarding
Feed field observations and customer feedback back to the product and engineering team
May also include travel to customer facilities as required for on-site commissioning and support
Requirements
Other Essential Requirements:
Must have existing right to work in Singapore
Fluent in English
Highly Desirable:
Benefits
Equity participation with the potential to share in the company’s long term success
Opportunity to work on real world physical AI systems applied to biomanufacturing
Build algorithms that move from experimental data to production scale systems
Exposure to a fast growing field at the intersection of machine learning, biology and industrial automation
Opportunity for significant responsibility and rapid career progression as the technology scales
Contribute to technologies enabling sustainable food and medicine production
Backed by the University of Cambridge Judge Business School and leading international venture capital investors
Potential for a full time role and competitive salary following successful completion of the project
The world’s food and medicine systems depend on biology that remains too costly and difficult to scale. Cellcraft IQ gives bioreactors the AI intelligence to optimise themselves, enabling cultivated meat, cell therapies, and fermentation products to reach global scale.
Your next opportunity is in here somewhere. Sign up to explore 52,000+ startups and their open roles. No spam. No gamification. Just jobs.
52,000+
Startups
65,000+
Open Roles
1,400+
New This Week
Strong Python programming : NumPy, Pandas, SciPy, scikit-learn (production code, not just notebooks)
Control systems fundamentals : State-space representation, PID tuning, stability analysis
Time-series methods : Kalman filtering, ARIMA, or recurrent neural networks (LSTM/GRU)
Real-time systems experience : Low-latency data processing, asynchronous programming, embedded constraints
Industrial protocols : Modbus, OPC-UA, MQTT, or similar SCADA/IoT communication standards
Domain Knowledge
Understanding of feedback control in dynamic systems.
Experience working with noisy sensor data and signal filtering techniques.
Ability to interpret process dynamics from time-series data (lag, dead time, oscillations)
Degree in Control Engineering, Computer Science, Chemical/Bioprocess Engineering, or related quantitative field
Bioprocess systems : Prior work with bioreactors, fermentation, or cell culture monitoring.
Model Predictive Control (MPC) implementation experience (cvxpy, CasADi, MATLAB MPC Toolbox)
Reinforcement learning for control (DQN, PPO, SAC)
Physics-informed ML : Incorporating mechanistic models (ODEs) into neural network architectures
Edge ML deployment : TensorFlow Lite, ONNX Runtime, or custom C++ inference
Signal processing : FFT, wavelet transforms, spectral analysis for biosensors (impedance, Raman)
Linux system administration : Docker, systemd services, remote deployment pipelines