Can you design and scale production RAG systems using LLMs and vector databases? Join our expert team to work on the security and alarms sector, contributing to the development of scalable RAG-based assistants and AI‐powered monitoring solutions that support multiple business initiatives across sites.
¿Le interesa este puesto? Puede encontrar toda la información relevante en la descripción a continuación.
At ERNI, you are never just a number. Even if you work on an external project, you will feel part of the team and always supported.
How do we make this happen?
With people. Besides your team and manager, you will have several support figures like a godparent, who will help you with the practical and administrative aspects of daily life during your first 6 months.
And the second most important person after you, your mentor, who will guide you through your entire onboarding and career at ERNI. You will have regular 1:1 meetings with them, and recurrently, you will work on your development plan to define your short‐, medium‐, and long‐term goals.
At ERNI, we highly value experience and technical knowledge. As a senior profile, you will have the space to continue growing, whether by deepening your technical skills or having greater influence on project decisions, with autonomy and the opportunity to share knowledge with other experts.
And if you are interested in mentoring, there is also space for that: supporting other ERNIans while still focusing on the technical excellence that sets us apart.
What You Will Bring
* Proven experience deploying RAG architectures in production including chunking strategies embeddings and retrieval optimization.
* Hands‐on experience with vector databases such as Pinecone, FAISS, ChromaDB, and OpenSearch.
* Solid AWS production experience with Bedrock, S3, Lambda, API Gateway and familiarity with MLOps patterns (SageMaker or equivalents).
* Practical experience with Langchain, Langraph, HuggingFace, Ollama, and integrating LLMs into production pipelines.
* Ability to integrate heterogeneous sources (PDFs, transcriptions, images, DBs, APIs) and ensure monitoring cost and latency optimization.
You will be responsible for designing and scaling RAG pipelines, including chunking and embeddings, and optimizing retrieval. You will integrate heterogeneous sources such as documents, transcriptions, images, databases and APIs. You will improve answer quality through prompt design, context ranking and hallucination mitigation. You will ensure production readiness by implementing monitoring, cost controls and latency improvements while collaborating with business stakeholders.
What if the project ends?
We work on a wide variety of projects, technologies, and sectors, allowing you to keep growing in different environments. If a project ends or you feel ready for a new challenge, we will find another one that aligns with your professional development.
Our working model
We ask you to be available for key meetings. Need to leave for a doctor's appointment or to pick up your child from school? No problem. We trust you to deliver quality work within your 40-hour workweek.
Our model is hybrid: we usually go to the office 2 days a week, though this depends on the project and team, but we love seeing each other's faces; the best stories always happen in the office!
You Will Also Enjoy
* We cover your certifications and reward technical achievements up to €1,400.
* Private health and travel insurance.
* Full coverage for sick leave + 1 extra day off per month without medical leave.
* Free emotional, legal, and family support.
* Gym discounts + sports compensation.
* Flexible remuneration: meals, transport, childcare, etc.
* Referral bonuses: up to €6,000 per candidate and €5,000 per client.
* 23 working days of vacation.
* Free language courses: English, Spanish, Catalan and German.
And the salary? xohynlm
We will discuss it during the first call. If it is important to you, feel free to ask!