onsite
AI Engineer with RAG / MCP
AI Engineer
AI Engineer focused on building Retrieval‑Augmented Generation pipelines and microservice‑based document processing solutions, leveraging Python, LLMs, and advanced prompt‑engineering techniques.
About the role
Key Responsibilities
- Design and implement end‑to‑end RAG pipelines for extracting structured data from unstructured documents.
- Develop and maintain microservice architectures that expose LLM‑powered APIs for document processing.
- Craft, test, and iterate prompts to optimize model performance across diverse document types.
- Integrate large language models into production systems, ensuring scalability, latency, and reliability.
- Collaborate with data engineers and product teams to define data schemas, evaluation metrics, and continuous improvement loops.
Requirements
- Strong proficiency in Python and experience building production‑grade APIs.
- Hands‑on experience with large language models (e.g., GPT, LLaMA) and Retrieval‑Augmented Generation techniques.
- Demonstrated expertise in prompt engineering and fine‑tuning for domain‑specific tasks.
- Solid understanding of microservice design, containerization, and orchestration (Docker, Kubernetes preferred).
- Ability to work independently, troubleshoot complex NLP pipelines, and deliver robust solutions on schedule.