AI developer
Summary
Designs and builds a production-grade LLM+RAG assistant for contextual data analysis, integrating external data sources, orchestrating multi-step agents, and deploying/fine-tuning models on dedicated or cloud infrastructure. Core stack: Python, SQL, OpenAI/Azure OpenAI/Claude APIs, RAG, Docker/MLOps.
Tech Stack:
∙ Python (5+ years)
∙ Strong working knowledge of SQL for data extraction and analysis (3+ years preferred)
∙ API integration with LLMs: OpenAI, Azure OpenAI, Claude
∙ ML/LLM architectures: RAG, embeddings, retrievers
∙ DevOps/MLOps: Docker, deployment of models on dedicated servers or cloud infrastructure
∙ Nice to have: FastAPI, vector databases (FAISS, Weaviate), prompt engineering
∙ Tools under consideration: LangChain or similar frameworks for rapid prototyping of LLM-based pipelines
Responsibilities:
∙ Design and build a production-grade LLM+RAG system for contextual data analysis
∙ Integrate external data sources and tools into the assistant’s knowledge base
∙ Set up and fine-tune LLMs on dedicated infrastructure or in the cloud
∙ Develop complex multi-step agents and orchestrated pipelines
∙ Build integrations with different platforms via API
∙ Ensure performance, scalability, and CI/CD automation of the ML systems
Requirements:
∙ Proven experience building real-world AI/ML products
∙ Deep understanding of the full machine learning lifecycle
∙ Experience working with popular LLM APIs and frameworks
∙ Ability to work independently and propose technical solutions
∙ Hands-on experience with LLM+RAG design patterns and prompt engineering