This role is in the early stages of hiring, and conversations are exploratory at this point.
A product-led SaaS company is integrating LLM-powered features directly into its core platform. This isn’t experimental, AI is central to the roadmap.
They’re looking for an engineer who understands how to build reliable, scalable LLM systems in production not just prompt or API integration.
You’ll work on:
Designing and deploying RAG pipelines
Improving inference latency and reliability
Embedding AI features alongside backend and product teams
Tech environment:
Python
LangChain (or similar)
AWS or GCP
Docker.
What matters:
Experience shipping LLM/NLP systems into production
Strong backend fundamentals (APIs, architecture, performance)
Understanding real-world trade-offs: cost, latency, scale
#J-18808-Ljbffr