About Wallapop
Wallapop is a Barcelona-based scale-up dedicated to empowering a more conscious and human way of consumption through a collaborative economy. Operating in Spain, Italy, and Portugal, Wallapop offers a vast catalogue of second-hand products and services, driven by technical innovation to make connected trade and second-hand the norm.
The Challenge
Wallapop generates billions of data points daily. With a mature data infrastructure, the Data Science and Machine Learning area is growing significantly. As a Senior ML Engineer, you will lead the evolution of the ML Platform and MLOps practice to support complex solutions in Personalization, Search, Trust & Safety, and Logistics. This role involves partnering with Data Scientists, Data Engineers, and DevOps to balance innovation with reliability, ensuring models scale efficiently for millions of users.
What You Will Do
- Iterate and maintain Wallapop’s ML Platform, identifying opportunities to improve speed, reliability, and maintainability, and define the long-term vision and roadmap for MLOps.
- Collaborate with Data Scientists to support their efforts, providing tools for efficient development, deployment, and monitoring of scalable models.
- Define and promote engineering best practices (coding standards, testing, CI/CD) within the ML domain.
- Partner with Data Engineering and DevOps to align ML development with company-wide infrastructure and data governance standards.
- Investigate and integrate new frameworks and tools (e.g., for LLMs or real-time inference) to maintain a modern and effective tech stack.
What We’re Looking For
- Proven experience building and owning production-ready ML platforms and pipelines, understanding the full lifecycle from experimentation to monitoring.
- Deep understanding of AWS components (SageMaker, Lambda, S3) and container orchestration with Kubernetes.
- Strong software engineering background with proficiency in Python, Git, and CI/CD workflows, demonstrating the ability to write robust, testable code.
- Experience with real-time ML architectures, leveraging tools like Kafka for low-latency ingestion and inference.
- Hands-on experience with vector databases or semantic search infrastructure (e.g., OpenSearch, Vertex AI), including indexing and retrieval tuning.
- Familiarity with the broader ML toolkit, such as orchestration/tracking tools (Flyte, MLFlow, Feast) and standard libraries (Pandas, Scikit-learn, TensorFlow/PyTorch).
- Professional proficiency in English, with the ability to explain complex technical concepts to diverse stakeholders.
What Would Be A Plus
- Hands-on experience working with LLMs, RAG architectures, and libraries like LangChain or LlamaIndex.
- Familiarity with Big Data technologies like Spark or Beam.
- Experience with Data Engineering tools such as Airflow, dbt, or Datahub.
- Experience with other cloud platforms like GCP or Azure in addition to AWS.