Skills : Python, vLLM,
An emerging specialization focused on designing how information is structured, retrieved, and fed into an LLMs context window — optimizing for relevance, token efficiency, and reasoning quality rather than model weights themselves.
Job Description:
An emerging specialization focused on designing how information is structured, retrieved, and fed into an LLMs context window — optimizing for relevance, token efficiency, and reasoning quality rather than model weights themselves.
Key Skills:
- Retrieval architecture design (chunking strategies, hybrid search, re-ranking)
- Prompt/context structuring and compression techniques
- Understanding of model attention/context-window behavior
- Data pipeline engineering for knowledge bases
- Experimentation and measurement of context-quality impact on output
Experience Required:
- 2–5 years in applied AI, search/information retrieval, or data engineering
- Experience with search systems (Elasticsearch, vector DBs) is a strong plus