This is a fully remote position, open to applicants in Spain.

• Design, implement, and deploy applications based on LLMs, from conception to production monitoring.

• Build RAG pipelines: Ingestion, Chunking, Hybrid Retrieval, Re-ranking, QA, and metrics.

• Develop advanced prompt engineering techniques, tool integration, workflows, agents, and multi-agent systems.

• Implement solutions using Python, Pandas, NumPy, scikit-learn, and NLP/LLM libraries.

• Utilize frameworks such as LangChain, LangGraph, FAISS, OpenSearch, or similar vector databases.

• Design tests and evaluations for LLMs: scoring, metric evaluation, performance analysis.

• Manage risks associated with generative AI: biases, hallucinations, RAI, privacy, and governance.

• Optimize the performance and cost of models in production by applying A/B testing.

• Coordinate with product, engineering, and design teams to align requirements and deliverables.

• Contribute to MLOps/LLMOps pipelines: CI/CD, testing, observability, APIs, deployments.

• Strong fundamentals in: Statistics.

• Machine Learning.

• SQL.

• Expert programming in Python and key libraries: Pandas, NumPy, scikit-learn.

• Pydantic.

• PySpark (desirable).

• Knowledge in LLMs: Prompt engineering.

• Embedding engineering.

• Optimization and evaluation of LLMs.

• Experience with: LangChain / LangGraph.

• FAISS, OpenSearch, or other VectorDBs.

• Experience in MLOps / LLMOps: Testing.

• Observability.

• REST API design.

• Serving applications (FastAPI, Flask).

• Integration with OpenAI or other services.

• Real-world experience with financial data, business analytics, or regulated environments (highly valued).

• Experience working in Agile, using Jira, Git, and CI/CD (Jenkins or others).

• Excellent communication skills with stakeholders.

• 23 vacation days per year.

• 14 payments, 12 monthly and two extra (June and December).

• Nursery ticket and medical + dental insurance.

Data Scientist / Machine Learning Engineer – LLMs, RAG, Python

People also viewed