Role Overview
As an AI Context Engineer, you will be responsible for bridging the gap between large language models (LLMs) and domain-specific data. You will design and implement sophisticated RAG (Retrieval-Augmented Generation) pipelines, optimize context window management, and ensure that our AI agents have the most relevant, high-quality information to perform complex tasks. With 5 years of experience in the field, you will lead the technical strategy for how we structure and retrieve data for our generative AI initiatives.
Key Responsibilities
- Design and maintain high-performance vector databases and indexing strategies to support contextual retrieval.
- Optimize prompt engineering workflows and context injection techniques to improve model accuracy and reduce hallucinations.
- Collaborate with Data Engineers to build robust ETL pipelines that transform unstructured data into AI-ready formats.
- Evaluate and benchmark various LLM architectures to determine the best fit for specific contextual requirements.
- Mentor junior engineers and contribute to the architectural roadmap of our AI platform.
Requirements
- 5+ years of experience in Software Engineering, with a strong focus on NLP or AI/ML production systems.
- Proven expertise in Python and frameworks such as LangChain, LlamaIndex, or Haystack.
- In-depth knowledge of vector databases (e.g., Pinecone, Weaviate, Milvus) and embedding models.
- Experience with cloud infrastructure (AWS/Azure/GCP) and containerization (Docker/Kubernetes).
Nice-to-Have
- Experience with fine-tuning open-source models (e.g., Llama 3, Mistral).
- Background in Knowledge Graph construction and integration with LLMs.
- Contributions to open-source AI projects.