SR Data Scientist

1. Large Language Models (LLMs) & Retrieval-Augmented Generation (RAG)

• Experience implementing RAG in production, with a deep understanding of nuances (chunking, ranking, etc.).
• Expertise in LLMs: Designing chains of LLM prompts, Evaluating LLM outputs (manual evaluation and using LLMs as judges).
• Selecting appropriate models (e.g., Sonnet, GPT series).

2. Prompt Engineering

• Ability to design multi-step LLM prompt chains (from initial to final prompts).

4. Python

• Proficient in data processing and analysis.
• Skilled in scripting and coding (mainly scripting, limited coding).

3. Data Engineering Experience

• Understanding of CI/CD pipelines.
• Knowledge of databases: SQL DB, Solr/OpenSearch.

🌟 Nice-to-Haves

• Experience with LangChain and LLaMA models.
• Familiarity with Agentic RAG and agents.
• AWS Hands-