Prompt and Context Engineer
A technical role focused on building and optimizing LLM-powered systems, prompt workflows, information retrieval, and integrations that improve the quality of model responses.
Обязанности
- Develop and implement API integrations using Python.
- Work with LLMs and language models.
- Design, write, and optimize prompts.
- Organize, tag, and manage organizational information for intelligent retrieval.
- Build and operate RAG pipelines using vector databases such as Pinecone, Weaviate, and Milvus.
- Measure and improve response quality using metrics including precision, recall, and hallucination rate.
- Conduct A/B testing and analyze model performance.
- Translate business needs into technical requirements.
- Collaborate with data, development, and product teams.
Требования
- Practical experience with Python.
- Practical experience developing API integrations.
- Understanding of data structures, information systems, and SQL and NoSQL databases.
- Familiarity with vector databases and RAG pipelines.
- Understanding of language models and hands-on experience with LLMs.
- Knowledge of prompt engineering and query optimization.
- Analytical ability to measure and improve response quality.
- Ability to translate business needs into technical requirements.
- Ability to collaborate with technical and business stakeholders.
Будет плюсом
- Experience with information architecture.
- Experience with A/B testing or model performance analysis.