Deep Reinforcement Learning Data Scientist

Deep Reinforcement Learning data scientist

BeChained built a solution for industrial manufacturers to optimise and reduce energy costs and carbon offset spent. Our RL solution, integrated with the existing facilities, continuosly identifies the optimal settings on machines and executes the improvement automatically. We also unlock demand-response and carbon market opportunities.

By applying to this position, you'll be part of an AI-powered solution making strides in energy efficiency, carbon accounting and demand-response in industry. You will have the chance to work in a dynamic start-up environment with international exposure to both EU and US markets.

Our Data Operations team handles actionable data products for businesses. Data scientists and engineers work together to create highly scalable solutions.

We bring state-of-the-art algorithms into production : we manage MLOps in an automated Cloud environment. Multi agent Deep Reinforcement Learning is our favourite. You will handle coding with Python, PyTorch, Tensorflow, Pandas, Scikit, Numpy, etc.

Minimum background :

Must have : MSc or higher degree (preferably a Ph.D.) in Computer Science or Engineering experience Great programming skills in Python, in a Linux / Mac based environment. MUST HAVE : previous experience in Reinforcement Learning in industry. You are a well-versed data scientist. Have hands-on experience with optimisation model (2 years experience in deep reinforcement learning multi agent), time series forecasting, recommendation engines, mathematical optimisation. Better if you have at least deep knowledge in the first two of them. Multiple work streams excite you : use ambiguity as a lever for opportunity for high-level thinking. We collaborate through version control (Git) and CI / CD systems to build technological roadmap with real time data. Have experience creating data product strategies with Python and time series, in open source software development, with the caveats of jupyter notebooks. Good English oral and written communication skills (Spanish or Italian are a plus) Autonomy in decision making, being the milestone to build. 2 years experience in common cloud based environments (AWS, Google Cloud Platform or Azure)

Soft skills :

We look for passionate, proactive, highly collaborative talent, solving problems and add business value. Strong sense of ownership and a growth mindset, like a start-up founder. Ability to clearly articulate the problem at hand in a simple, actionable way. We look for long-term inspiring talent, with creativity and learning objectives. You can jump into the code on a deep level, but you are also able to contribute to long-term initiatives.

About The Job

At BeChained, our mission is to prevent 65 millions tCO2 per year in the industrial processes by 2040, by reducing energy use, lowering dependency on fossil fuels, and foster decarbonization of the energy system. The

RL data scientist

will play a vital role in expanding our footprint in any industry. The individual will work closely with our data lead to build RL / ML pipelines to provide an actionable solution to customer pain points, and support both technical and economic proposals.

This position offers an incredible opportunity for a passionate individual with a green heart, looking to be part of a genuine, impact-driven project. Your work would be done at either Barcelona office and remotely with flexible working hours.

Responsibility

To build AI agents specialised in manufacturing process with Deep Reinforcement Learning models. Extend the production control to the whole production chain. Identify the best RL models, process parameters and setting for each machine. Roll out scalable optimisation pipelines. Code in Cloud-based infrastructure and keep version up to date with Git. Improve existing products, find better models and architectural patterns. Being agnostic from hardware, unlock the access from a massive amount of data. Design / build, test & deploy new libraries & APIs. Keep the highest standards of testing & code quality. Use technologies, i.E. Python, PyTorch, Tensorflow, Pandas, Scikit, Numpy, Dockers / Kubernetes on Linux. Envision new insights from client's real time industrial data. Build tools for frictionless delivery to facilities.

Nice to have

Have experience in building libraries, APIs and scalable platform services. Hands on end-to-end ML / RL lifecycle. Collaborate with other roles to bring RL / ML into production. Design optimisation models and components for distributed systems (e.G. in micro-service architectures). Roll out scalable software & products to process data (e.G. real-time components, REST services). Use data storage (e.G. time series databases, key-value stores) & data processing technologies (e.G. Kafka, Spark, Airflow, AWS Glue,...)

An inspiring place to work

Job location : Operation Team works at Norrsken House in Barcelona, in front of the beach! Required a WORK PERMIT for Spain. Check our web ( and twitter