We're seeking a Senior Data Scientist to lead the development of advanced AI solutions that power deep research, scientific reasoning, and strategic decision-making. You'll work with large language models (LLMs), retrieval-augmented generation (RAG) systems, and Graph-RAG architectures to create intelligent tools that extract and synthesize insights from complex, unstructured data.
This role is ideal for someone who thrives at the intersection of machine learning, knowledge representation, and real-world impact, and who is excited to help shape the future of how research is conducted in global health, legal, scientific, and financial domains.
What You'll Do
* Design and develop LLM-powered applications for tasks such as document analysis, summarization, knowledge extraction, and reasoning.
* Build and optimize RAG pipelines with custom retrieval logic, vector databases, and hybrid search strategies.
* Implement and integrate knowledge graphs into AI systems for enhanced explainability and structured reasoning (Graph-RAG).
* Own the full pipeline from data ingestion and preprocessing (e.g., PDFs, scientific papers, grant documents) to model deployment.
* Collaborate with engineers and domain experts to define requirements, evaluate outputs, and iterate rapidly.
What You Bring
* M.Sc. or Ph.D. in Computer Science, or related field.
* Proven experience with LLMs, including prompt design, fine-tuning, and evaluation.
* Strong understanding of retrieval-based systems (e.g., FAISS, Weaviate, Elasticsearch, Pinecone).
* Experience with LangChain, LlamaIndex, HuggingFace Transformers, and PyTorch.
* Familiarity with knowledge graph design and integration (e.g., Neo4j, RDF, NetworkX).
* Solid software engineering practices and hands-on coding ability in Python.
* Experience with cloud-based or on-prem AI deployments, ideally in secure or hybrid environments.
* Ability to lead projects independently, collaborate cross-functionally, and explain complex technical concepts clearly.
Nice to Have
* Familiarity with Graph-RAG, Anthropic's MCP, or agentic system orchestration.
* Experience working with sensitive, domain-specific data (e.g., healthcare, global development, legal).
* Contributions to open-source projects, publications, or technical blogs.
* Knowledge of scientific reasoning, ontologies, or structured metadata in research workflows.
Why Join Us
* Shape the next generation of AI research tools grounded in real-world needs.
* Join a fast-paced, mission-driven team with opportunities to own high-impact projects.
* Flexible, remote-friendly environment with strong learning and innovation culture.
Job Type: Full-time
Pay: R$10,000.00 - R$20,000.00 per month