AI Context Engineer
Posted 35ds ago
Employment Information
Report this job
Job expired or something wrong with this job?
Job Description
Context Engineer designing and optimizing AI information architectures. Focused on LLMs and context management to improve AI outputs.
Responsibilities:
- Design and implement context pipelines for LLM-based systems.
- Structure information to maximize model understanding and response quality.
- Define strategies for prompt composition, context injection, and tool usage.
- Build and optimize RAG pipelines using vector databases.
- Implement document ingestion, chunking, embedding, and retrieval strategies.
- Improve retrieval precision and reduce hallucinations in AI outputs.
- Design and maintain prompt frameworks for AI agents and applications.
- Optimize prompts through systematic testing and evaluation.
- Integrate prompts with tool use, APIs, and agent workflows.
- Structure knowledge bases for AI consumption.
- Implement pipelines for data preprocessing, indexing, and embedding generation.
- Manage semantic search and knowledge retrieval systems.
- Analyze model performance and improve context efficiency.
- Monitor latency, token usage, and system scalability.
- Develop evaluation methods to measure prompt and context performance.
- Work closely with AI Engineers, Data Engineers, and Product Teams.
- Translate business requirements into AI-powered solutions.
- Document context architectures and AI workflows.
Requirements:
- Strong experience working with LLMs (OpenAI, Anthropic, open-source models, etc.)
- Experience building RAG systems
- Knowledge of vector databases (Pinecone, Weaviate, Qdrant, Chroma, etc.)
- Understanding of embeddings and semantic search
- Experience with prompt engineering and prompt evaluation
- Programming skills in Python or TypeScript
- Experience with API integrations
- Understanding of LLM limitations, hallucinations, and context windows
- Knowledge of token optimization strategies
- Familiarity with agent frameworks (LangChain, LlamaIndex, Semantic Kernel, etc.)
- Experience working with structured and unstructured data
- Knowledge of JSON, APIs, and data pipelines
- Strong analytical and problem-solving mindset
- Ability to experiment and iterate rapidly
- Clear technical documentation skills
Benefits:
- Health insurance
- Retirement plans
- Paid time off
- Flexible work arrangements
- Professional development












