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
Full job description
Uncountable is seeking experienced engineers to lead the transformation of our platform into an AI-first R&D ecosystem. We are building the next generation of tools that empower scientists at Fortune 500 companies to accelerate discovery through Generative AI. As an LLM Applications Engineer, you will be the architect of our LLM infrastructure. You won't just be building interfaces; you will be designing the retrieval systems, agentic workflows, and data pipelines that bridge the gap between complex experimental data and actionable AI insights. Your work will directly modernize how the world’s leading researchers interact with their data.
Primary Responsibility
Your primary responsibility is to design, build, and scale the LLM infrastructure and user-facing AI features of the Uncountable Web Platform. This is a hybrid role requiring a deep understanding of full-stack development and the unique challenges of deploying LLMs in production.
Infrastructure:
- Implement and optimize RAG (Retrieval-Augmented Generation) pipelines, vector databases, and prompt management systems.
Feature Development:
- Build intuitive, AI-driven UI components that allow scientists to query, analyze, and visualize complex experimental datasets.
Integration:
- Connect LLM capabilities with our core SQL databases and data analysis engines to ensure high-fidelity, grounded AI responses.
Salary Range:
- $130K–$175K + Equity
Requirements
- 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.
Nice to have
- 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.
What we offer
- Competitive Salary and Equity
- Health and Dental Insurance
- 401K with Employer Contribution
About us
Learn more about Interviewing at Uncountable
Learn more about our engineering team: Check out our blog
