Developer and Operations Engineer

JOB DESCRIPTION 

Ref: 2025-1

Job Title: DevOps Engineer 

About EAS

Energy consumption of data centers has become a real issue for economic and ecological reasons.

With Energy Aware Solutions data centers get more Performance per Watt! Our startup believes in efficient computing in HPC and AI. EAS is a service company providing installation, consulting, and support on Energy Aware Runtime software (EAR) and in general energy and power management. EAS is also co-developing the EAR software with the Barcelona Supercomputing Center and in particular the GPU energy optimization module which provides about 20 % of energy savings. EAR is transparent, independent from vendors, live at runtime, modular and easy to use. The Energy Aware Solutions S.L. is a BSC-UPC Spin Off created in September 2020 with the aim of innovating and providing professional services and in the context of energy management and optimization for HPC & AI Data Centers. EAS headquarters is in Barcelona with an international team (Spanish, French, Italian) working in Barcelona or remotely. EAS technology is based on the EAR software. EAR is a European software tool for energy monitoring, management and optimization developed by BSC and EAS. EAR software is installed in many large European supercomputing systems like EDF in France, LRZ in Germany, SURF in the Netherlands and BSC-MN5 in Spain. Our aim is to grow in number of customers and customer satisfaction. EAS is also participating in two European R&D  projects DYMAN and ODISSEE funded under The European Innovation Council (EIC). 

Context and Mission

EAS technology is installed in many European HPC Data Centers. It is EAS responsibility to guarantee EAS software is installed, configured and tuned following the customer requirements (hardware and software),  without affecting the operations and getting the maximum performance with less power consumption. The candidate will take the responsibility of being part of the EAS team in charge of the customer relation-ship: installing, validating and optimizing  EAR configuration for each customer. This is not a classical consulting job since the optimization of the software includes the computation and evaluation of energy models and policies adapted to the customers. Because of that, the candidate must have some skills of system administration to be able to install EAR  and understand the relationship with other system tools and also about parallel applications performance evaluation in HPC/AI Data centers. No prior knowledge on the EAR software is required. EAS already offers high quality technical support to our customers. The candidate will participate in customer-specific developments and will identify, report and potentially fix issues in the EAR software to guarantee a 24/7 availability of the software.

About the team

We are an international team of 10 engineers working both in supporting our customers and developing EAR software. We are looking to expand both teams.

Key Duties

After some training period, the candidate will have to:

• EAR installation and validation

• Optimization of the EAR configuration for each customer

• Execution and validation of training phase to  compute the energy models and tuning of the energy policies

• Performance and power evaluation of HPC/AI applications when applying optimization policies

• Guarantee the customer satisfaction by providing a high quality L3 technical support of EAR 

Requirements

• Education

  • Bachelor degree or MSc in Computer Science or related discipline.  

• Knowledge and Professional Experience

• Mandatory

  • Experience with UNIX/LINUX environments

  • To have good skills and experience in C programming

  • Experience on using HPC environments: Parallel jobs execution and SLURM scheduler utilization. Skills on execution and evaluation of HPC and/AI applications in Data Centers. Applications include traditional MPI applications and other frameworks such as tensorflow. Previous expertise on user experience in HPC/AI data centers will be highly valuable..

• Basic experience on system administration and software installation

• Competences

  • Candidates must be proactive, self-motivated individuals who can understand technical concepts

  • Mandatory: Excellent written and verbal communication skills in English

  • Ability to take initiatives, prioritize the tasks and work under defined deadlines

Conditions

We offer a full-time contract, a good working environment, flexible hours and hybrid work (Barcelona). Salary will depend on the qualifications and experience of the candidate. The selected candidate will be trained by the EAS team on the EAR software during the first 3 months of the contract. 

Applications Procedure

Applications should be sent to contact@eas4dc.com and include:

• A letter explaining your interest in the job, the company,  and your salary expectation

• A full CV including contact details and references

• Ref: EAS20251