Role overview
We are looking for a Senior Data Scientist I to help design, build, and evaluate advanced AI capabilities powering LeapSpace. This role will focus heavily on applied AI research and development , including prototyping intelligent workflows, integrating large language models with trusted scientific data, and advancing AI-assisted research experiences.
You will work across retrieval systems, generative AI, reasoning workflows, evaluation frameworks, and AI experimentation , helping shape the future of AI-powered scientific discovery at Elsevier.
This role is ideal for someone with strong hands-on experience in applied AI, NLP, retrieval systems, and LLM-based applications , who enjoys rapidly prototyping and translating emerging AI techniques into scalable product capabilities.
Responsibilities
- Lead prototyping and development of LLM-powered research workflows , including: Scientific question answering Literature summarization Semantic exploration and discovery Research insight generation Citation-aware reasoning workflows
- Scientific question answering
- Literature summarization
- Semantic exploration and discovery
- Research insight generation
- Citation-aware reasoning workflows
- Design and iterate on agentic and multi-step AI workflows using frameworks such as LangGraph and related orchestration tooling.
- Apply state-of-the-art techniques in: NLP Generative AI Embeddings and semantic representations Retrieval-augmented generation (RAG) AI reasoning and orchestration
- NLP
- Generative AI
- Embeddings and semantic representations
- Retrieval-augmented generation (RAG)
- AI reasoning and orchestration
- Rapidly evaluate emerging AI models, tooling, and frameworks to identify opportunities for product innovation.
- Translate applied AI research into scalable, production-oriented solutions that improve researcher productivity and trust.
- Contribute to experimentation around prompt engineering, context management, grounding strategies, and hallucination mitigation.
- Support integration of scientific metadata, ontologies, and knowledge assets into AI workflows.
- Design and optimize search and retrieval pipelines , including lexical, vector, and hybrid retrieval approaches.
- Develop and improve RAG systems that integrate LLMs with trusted scientific and biomedical content.
- Experiment with embeddings, re-ranking models, chunking strategies, and retrieval orchestration to improve relevance and answer quality.
- Build scalable workflows for semantic search and knowledge discovery.
- Collaborate closely with engineering teams to productionize AI and retrieval systems.
- Develop and evolve evaluation frameworks for search and AI systems, including: IR metrics (e.g., NDCG, recall, precision) LLM and RAG evaluation metrics (e.g., grounding, faithfulness, hallucination detection)
- IR metrics (e.g., NDCG, recall, precision)
- LLM and RAG evaluation metrics (e.g., grounding, faithfulness, hallucination detection)
- Design offline evaluation methodologies and contribute to online experimentation and A/B testing.
- Build and maintain evaluation datasets, benchmark suites, and annotation strategies.
- Drive rigorous experimentation to measure system improvements and user impact.
- Contribute to responsible AI practices, including quality, reliability, and trust evaluation.
- Partner with product managers, engineers, UX researchers, and domain experts to deliver impactful AI capabilities.
- Translate complex technical findings into actionable recommendations for stakeholders.
- Contribute to technical strategy and roadmap discussions for LeapSpace AI capabilities.
Basic qualifications
- Master’s or PhD in Computer Science, Data Science, Machine Learning, NLP, Information Retrieval, or a related field
- ~3–5+ years of experience in applied AI, machine learning, NLP, or information retrieval
- Strong hands-on experience with: LLM-based applications and generative AI systems RAG pipelines and retrieval systems Search and retrieval architectures (lexical, vector, hybrid) Evaluation methodologies for IR and generative AI systems
- LLM-based applications and generative AI systems
- RAG pipelines and retrieval systems
- Search and retrieval architectures (lexical, vector, hybrid)
- Evaluation methodologies for IR and generative AI systems
- Advanced programming skills in Python
- Experience with modern AI/ML frameworks and tooling (e.g., PyTorch, Hugging Face, LangChain, LangGraph , Haystack)
- Experience working with Databricks or similar distributed data/ML platforms
- Strong understanding of experimentation design, evaluation frameworks, and statistical analysis
- Proficiency with data visualization and analytical tooling (e.g., Tableau, Power BI, matplotlib, seaborn)
Preferred qualifications
- Experience building AI assistants, agentic workflows, or conversational AI systems
- Experience working on large-scale search, ranking, or recommendation systems
- Familiarity with scientific, biomedical, or scholarly datasets
- Experience with knowledge graphs, ontologies, or semantic enrichment systems
- Exposure to production ML systems and MLOps practices
- Publications or applied research contributions in NLP, IR, search, or generative AI
- Experience building AI systems in regulated, high-trust, or content-rich domains
About the company
- Search and retrieval systems
- Generative AI and LLM applications
- AI evaluation and experimentation
- Semantic enrichment and knowledge systems
- Scalable AI platforms and intelligent workflows
Tags & focus areas
Used for matching and alerts on DevFound Fulltime Ai Data Science Generative Ai