LLM Applications Engineer
Required skills
2+ years of software development experience with a focus on full-stack web applications, Proven experience with LLM orchestration frameworks (e.g., LangChain, LlamaIndex, or Haystack), Proficiency in Python and JavaScript/TypeScript: Ability to work across the AI backend and the React frontend, Solid Engineering Fundamentals: Experience with API design, asynchronous processing, and performance optimization
Preferred skills
B.S. in Computer Science or a related technical field, Experience with LLM Evaluation: Knowledge of how to measure and mitigate "hallucinations" in a scientific/technical context, Familiarity with SQL: Specifically optimizing queries that serve as the context for LLM prompts, Product Mindset: A passion for creating "LLM-first" user experiences that feel seamless rather than bolted-on
Technologies
Python, JavaScript/TypeScript, React, SQL, LLM orchestration frameworks (e.g., LangChain, LlamaIndex, or Haystack), RAG (Retrieval-Augmented Generation) pipelines, vector databases, prompt management systems
Responsibilities
Design, build, and scale the LLM infrastructure and user-facing AI features of the Uncountable Web Platform, Implement and optimize RAG (Retrieval-Augmented Generation) pipelines, vector databases, and prompt management systems, Build intuitive, AI-driven UI components that allow scientists to query, analyze, and visualize complex experimental datasets, Connect LLM capabilities with our core SQL databases and data analysis engines to ensure high-fidelity, grounded AI responses
Seniority
Not specified
Domain
AI/ML, Web Development, Data Science
