Position Details
About this role
NewtonX is hiring a Software Engineer to build the core LLM infrastructure powering two B2B research products: Hub and Prime. The role focuses on production-quality implementation of LLM integrations, semantic search, and automated expert knowledge capture at scale.
Key Responsibilities
- Own core LLM infrastructure for Hub and Prime
- Build self-serve B2B research features using RAG and adaptive workflows
- Architect automated systems to capture expert opinions into longitudinal datasets and dashboards
- Implement semantic search across proprietary corpora
- Maintain research-grade quality with testing and code reviews
Technical Overview
You will develop full-stack features (React, TypeScript) and backend services (Python and/or Node.js) that integrate Large Language Models (LLMs) via OpenAI APIs and Anthropic APIs. The systems will run on AWS using Docker, with an emphasis on RAG (Retrieval Augmented Generation), embeddings, and semantic search across proprietary corpora.
Ideal Candidate
The ideal candidate is a mid-level software engineer with 3-4 years of production engineering experience, strong full-stack skills in React and TypeScript, and backend experience with Python or Node.js. They have hands-on experience integrating Large Language Models (LLMs) using OpenAI APIs and/or Anthropic APIs, and can build production AI pipelines with a quality mindset (testing and code reviews).
Must-Have Skills
Nice-to-Have Skills
Tools & Platforms
Required Skills
Hard Skills
Soft Skills
Industry & Role
Keywords for Your Resume
Deal Breakers
3-4 years of experience shipping production code in a fast-paced environment, Hands-on LLM integration experience with OpenAI/Anthropic APIs, Experience with AWS and Docker
Get matched to jobs like this
Luna finds roles that fit your skills and career goals — no endless scrolling required.
Create a Free Profile