Prompt Engineer/Data Analyst

We are seeking a Prompt Engineer/Data Analyst to join our team. This hybrid role blends strong data analysis expertise with emerging AI capabilities to optimize Generative AI systems and ensure high data quality for AI-driven initiatives. The ideal candidate is analytical, detail-oriented, and passionate about improving LLM-based solutions to deliver measurable business value.

What You’ll Do

• Design, test, and optimize prompts for various LLM applications (GPT-4, Claude, Llama).
• Develop reusable prompt templates and implement advanced techniques (few-shot, chain-of-thought, structured prompting).
• Conduct A/B testing to evaluate and improve prompt performance across different models.
• Prepare, clean, and validate datasets for fine-tuning and RAG systems.
• Build and maintain data pipelines to feed structured context into AI systems.
• Define, track, and report KPIs such as accuracy, latency, and cost efficiency.
• Develop evaluation frameworks to assess LLM outputs (relevance, factuality, consistency).
• Create dashboards and reports to communicate AI performance and impact to stakeholders.
• Maintain prompt libraries, knowledge bases, and documentation for AI systems.
• Collaborate with cross-functional teams including Engineering, Product, and QA in Agile environments.
  
  

What You Know

• 4+ years of experience as a Data Analyst, Business Analyst, or similar role.
• Strong proficiency in SQL for data extraction and analysis.
• Hands-on experience with Python (pandas, numpy) for data manipulation.
• Experience working with LLM APIs (OpenAI, Anthropic, or open-source models).
• Solid understanding of prompt engineering techniques and LLM behavior.
• Experience with RAG systems and vector databases.
• Experience with data visualization tools (Tableau, Power BI, or similar).
• Basic knowledge of APIs, JSON/CSV formats, and Git version control.
• Comfortable working in cloud environments (AWS, Azure, or GCP).
  
  

Secondary Skills (Nice To Have)

• Knowledge of vector embeddings and semantic search.
• Familiarity with LangChain, LlamaIndex, or similar frameworks.
• Experience working in Agile environments using Jira/Confluence.
• Background in software testing, QA, or SDLC processes.
• Experience in enterprise domains (financial services, insurance, retail).
  
  

Education

• Bachelor’s degree in computer science, Data Science, Information Systems, or a related field.