We’re looking for a Data Scientist to build production-grade AI agent systems that automate multi-step workflows, interact with data in real time, and drive measurable business outcomes—helping shape the future of privacy-first, neuro-contextual advertising. 🤖📈🔒

🎯 Responsibilities

1. Build AI agent systems that interact with data, execute multi-step workflows, and make autonomous decisions in production.
2. Design and implement agent architectures using modern frameworks, including multi-agent orchestration, delegation patterns, and reliability under production constraints.
3. Solve context management challenges (conversation history, tool outputs, file attachments) using semantic search / retrieval so agents consistently have the right information.
4. Integrate agents with databases and APIs for real-time tool calling, and create scalable tool-integration patterns (e.g., protocols like MCP) for broader adoption across teams.
5. Develop evaluation frameworks to measure agent performance in production and iterate based on results.
6. Own solutions end-to-end: from concept and design to deployment, working closely with cross-functional stakeholders to align work with business goals.

🛠️ Requirements

1. 3–5 years building and deploying production ML systems, including hands-on work with LLM-based applications or autonomous agents (e.g., Pydantic AI, OpenAI Agents SDK, LangGraph, or similar).
2. Strong software engineering skills in Python, with experience shipping services to production (async programming, API design).
3. Production infrastructure experience with Docker and Kubernetes.
4. Strong quantitative background (CS, Engineering, Statistics, Math, or similar) and understanding of retrieval systems, embeddings, and context-management patterns.
5. Experience delivering end-to-end projects (design → deployment), comfortable with tool calling, multi-step workflows, and the non-deterministic nature of LLM systems.
6. Proactive, adaptable, and entrepreneurial mindset—comfortable operating where best practices are still emerging.

🧰 Tech environment (what you’ll work with)

1. High-scale ML serving (very low latency at high throughput).
2. Microservices in Python and Go, deployed on Kubernetes in GCP (and AWS).
3. Data infrastructure including datalakes, GCS, Redis, Kinesis and/or Kafka, and large-scale daily data outputs for analytics.
4. Broader company stack also includes TypeScript/Node.js and Scala, with technologies like Kafka, Druid, and MongoDB in GCP.

🤝 Why join

1. High-growth moment with strong career development opportunities.
2. Remote-first culture with flexibility to work 100% remote or hybrid (depending on what works best).

🎁 Benefits & perks

1. Learning: ODILO online courses + optional English/Spanish group classes.
2. Flexible benefits plan (restaurant, transportation, kindergarten vouchers).
3. Health insurance.
4. Gympass / wellbeing programs.
5. Seedsave discounts program.
6. Home office budget up to 1,000€ gross (equipment like screen/chair/desk).
7. Paid trips to HQ in Madrid for in-person squad collaboration.
8. MacBook Pro M3.

📍 Location / Work model

1. Remote-first (100% remote or hybrid).
2. Contracts available within Europe where legal entities exist: Spain, Italy, UK, Belgium, Netherlands, France, Germany.