Work with RAG (Retrieval-Augmented Generation) architecture
Implement structured output, retry logic, and reduce model hallucinations
Optimize hardware and manage cost efficiency in LLM applications
Use LLM evaluators and implement few-shot learning strategies
Work with vector databases and semantic search services
Implement or support hybrid search (bonus)
Perform LoRA fine-tuning (bonus)
Strong experience with PySpark
Proficient in Python for data science
Solid understanding of statistics and machine learning techniques
Experience with LLMs and data science frameworks
Familiarity with cost and performance optimization
Jobseeker
Recruiter