Backend Engineer – Python & Generative AI

INNOCV Solutions S.L.U.; Madrid; Presencial; EUR 60.000 - 90.000; Jornada completa

Ventajas ofrecidas por este puesto de trabajo

Professional training & certifications

Flexible hours

Short Fridays & summer 7h

Extra vacation days every 3 years

Day off on your birthday

Bring a friend benefit

Flexible compensation

Gympass

Volunteering opportunities

Team events & outings

Descripción de la vacante

INNOCV Solutions S.L.U. in Madrid is seeking a Backend Engineer with strong Python expertise to design, develop and operate generative AI backends.

You will build services powered by LLMs, agentic workflows and retrieval-augmented generation, aiming for reliability and scalability. You will turn AI prototypes into production-ready systems, work with LangChain, Azure OpenAI, and FastAPI, and contribute to observability and testing.

Formación

• 5+ years of professional backend development experience with Python.
• 2+ years of hands-on experience delivering LLM-based solutions in production.
• Experience with Azure OpenAI and/or the OpenAI API.
• Practical experience with LangChain and LangGraph.
• Experience building production RAG systems using Azure AI Search or similar technologies.
• Strong knowledge of FastAPI, asynchronous programming and streaming.
• Experience with LLM evaluation and observability.
• Professional working proficiency in English.

Responsabilidades

• Design, develop and maintain backend services powered by Large Language Models (LLMs), agentic workflows and Retrieval-Augmented Generation (RAG) architectures.
• Focus on reliability, scalability, evaluation and observability of AI systems.
• Turn AI prototypes into robust, production-ready systems and contribute to AI engineering practices.

Conocimientos

Python

LLM in prod

Azure OpenAI

LangChain

FastAPI

Async & streaming

Observability

AI coding tools

English proficiency

Herramientas

LangGraph

LangChain

Azure OpenAI API

Azure AI Search

Databricks

Descripción del empleo

Who are we?

We are part of the Alkemy Group, specializing in driving growth through our technological expertise, tackling complex challenges, and fostering operational excellence.

• We are digital natives and technology-neutral thanks to our rapid adaptation capabilities and problem-solving skills in any business situation.
• We are passionate about technology challenges that have a significant impact on business. To address these, we have high-performance teams and the ability to quickly and effectively combine technologies.
• We support our clients in their digital evolution to achieve maximum efficiency in their businesses, leveraging our extensive multi-sector experience.

We invite you to get to know us in depth by exploring the various sections of our website.

What are we looking for?

We are looking for a Backend Engineer with strong Python expertise and hands-on experience building and operating Generative AI solutions in production.

You will design, develop and maintain backend services powered by Large Language Models (LLMs), agentic workflows and Retrieval-Augmented Generation (RAG) architectures. The role combines solid software engineering practices with advanced AI engineering, focusing on reliability, scalability, evaluation and observability.

We are looking for an engineer who can turn AI prototypes into robust, production-ready systems and contribute to the evolution of our AI engineering practices.

What do we value?

• 5+ years of professional backend development experience with Python.
• 2+ years of hands-on experience delivering LLM-based solutions in production.
• Experience with Azure OpenAI and/or the OpenAI API.
• Practical experience with LangChain and LangGraph.
• Experience building production RAG systems using Azure AI Search or similar technologies.
• Strong knowledge of FastAPI, asynchronous programming and streaming.
• Experience with LLM evaluation and observability.
• Experience using AI coding tools such as Claude Code or Codex, and working with skills and MCP servers.
• Professional working proficiency in English.

Nice to have

• Experience with Azure AI Foundry or Azure AI Document Intelligence.
• Familiarity with Langfuse, MLflow or Databricks.
• Knowledge of spec-driven development (SDD).
• Experience deploying and monitoring AI applications in enterprise cloud environments.

What do we offer you?

In this company, you can be yourself and work with colleagues equally passionate about technology and innovation, ready to support you at all times. We want to see you evolve and grow with us. To that end, we invest in your professional development with training, tech breakfasts, and attendance at forums. We are advocates of continuous learning, which is why we provide a personal budget for staying up to date with market trends.

We care about well-being and happiness at work, which is why we listen to needs to offer the best working conditions in a unique human environment. Due to the emphasis we place on flexibility and work-life balance, we won the Madrid Flexible Company Award in 2020 and received an honorable mention in 2022.

This is a WIN-WIN, here are some highlights:

Professional Training & Certifications

Flexible hours

Special timetable: Fridays and summer 7h.

Every three years, 6 extra days off.

Day off on your birthday

Bring a friend and benefit from it

Flexible compensation

Wellness - Gympass

Volunteering opportunities

Company events and team buildings

To learn more about us, the protagonists of INNOCV will share more about the company.

If you identify with our work philosophy and share our passion for INNOvation and Code Vocation, we want to meet you!

We are committed to supporting the LGTBIQ+ community and invite individuals with disabilities to apply for this position. We value diversity and are committed to inclusion in our team.