.svg)
.svg)
.svg)
Machines learned to understand language. We’re teaching them to understand matter.
Forty percent of global manufacturing happens through physical and chemical processes inside pipes, tanks, and reactors. Despite decades of industrial automation, much of what happens inside them remains remarkably invisible. Manufacturing is the most ubiquitous and foundational sector in global economy, yet the way factories are fundamentally run have used the same control philosophies, manual operations, and legacy software for the past 60 years.
Laminar deploys state-of-the-art patented sensors and edge hardware directly into live production environments, generating data that didn’t previously exist to build foundation models deployed in factory floors that understand chemistry, composition, quality, and material state in real time. We use that understanding to run autonomy and rethink how things are made.
The last generation of industrial automation taught machines to execute instructions reliably. The next will teach them to understand the processes they control and run autonomously, adaptively, and agentically: higher quality, safety, more efficiently, sustainably, and productively.
That future is already taking shape. Today, Laminar works with 7 of the world’s 10 largest food and beverage manufacturers and operates across hundreds of factories globally across six continents. Our systems have materially reduced waste, cut manufacturing downtime, saved water, chemicals, energy, and helped prevent safety and quality failures. Our technology has gained international recognition, from being selected as a 2026 World Economic Forum Technology Pioneer, Gold 2026 Edison Award, Unilever Startup of the Year, to Innovator Awards by both Coca-Cola and AB InBev, and more.
We are backed by tier-one investors in physical AI to make intelligent, self-improving production the new standard for industry.
Join us to build what makes matter intelligible, and the intelligible controllable.
What You Will Do
- Build machine learning models for real-time processing and analysis of time-series data with high accuracy, low latency, and scalability.
- Use knowledge of ML theory and practice to improve current state-of-the-art for models using time-series sensor data.
- Develop generalizable, cutting-edge unsupervised models for time-series anomaly detection.
- Apply critical thinking and first principles knowledge to develop optimization algorithms for black-box systems.
- Collaborate with data scientists, software engineers, and other internal stakeholders to align ML models, ensuring they meet performance and reliability requirements.
- Deploy ML models to Edge compute devices and monitor performance using best practices for MLOps.
About You
- Highly knowledgeable in ML theory, architectures, and design.
- Proficient in Python. Strong candidates may also be proficient in C++.
- Experience using multiple ML frameworks (such as PyTorch, TensorFlow, Scikit-Learn, JAX) and numerical libraries (such as NumPy and Pandas). Knowledge of edge-specific frameworks (i.e. TensorFlow Lite) is a plus.
- Experience building ML models with time-series or sequential data (such as NLP), especially for long time sequences and real-time processing scenarios. Experience working with sensor data is a plus.
- Familiarity with reinforcement learning (RL), computational graphs, and/or graph neural networks is a plus.
- Knowledgeable in techniques to optimize ML models for inference in compute-limited scenarios (i.e. model distillation, pruning, dimensionality reduction, feature selection, parallelization).
- Familiar deploying models for fast, efficient inference on compute accelerators (TPUs or NPUs).Proficient in designing, implementing, and maintaining robust ML pipelines for end-to-end model lifecycle management. Experience benchmarking multiple models is a plus.
- Familiar deploying models in containerized settings, such as Docker. Knowledge of Kubernetes and/or Docker Swarm is a plus. Familiar with SQL or similar database systems (such as MySQL, PostgreSQL, MongoDB).
- Proficient in Git or other version control systems.
- Familiar with cloud platforms such as AWS, Azure, or Google Cloud.
- Experience working with LLMs/RAG is a plus, especially in building a company knowledgebase, chatbot, or for data analysis/summarization. Familiarity with Agile methodologies and experience in collaborative, cross-functional teams.
- Analytical thinker with the ability to solve complex problems efficiently.
- Excellent communication skills to articulate technical issues, solutions, and progress effectively.
- Adaptability to learn new technologies and adapt to evolving project requirements.
- Strong team player mindset, comfortable sharing knowledge and collaborating within a team environment.
- Familiarity with Agile methodologies and experience in collaborative, cross-functional teams.
- Analytical thinker with the ability to solve complex problems efficiently.
- Meticulous attention to detail in writing clean, maintainable code and designing robust database architectures.
- Excellent communication skills to articulate technical issues, solutions, and progress effectively.
- Adaptability to learn new technologies and adapt to evolving project requirements.
Benefits
- Direct impact on product and culture.
- Comprehensive benefits package including Medical, Dental, Vision, Life Insurance, Disability, Transportation benefit, Health and Wellness benefit, and more.
- 401k plan with employer matching
- Equity
- Competitive salary and bonus opportunities.
- Dynamic and inclusive work environment.
- Opportunities for growth and professional development.
- Access to Greentown Labs' extensive network of cleantech startups.
Learn How We Think
- Learn about our startup journey: Our Journey
- How we're combating climate change: AI-Powered Climate Tech
- A customer story: Ben & Jerry's uses H2Ok's precision automation to cut time & water usage
Why Laminar?
Our Interview Process
