We’re working on building production AI systems , not demos ,focused on real-world workflows, data pipelines, and integrating LLM-based systems into usable products.
Work includes:
- designing backend systems and APIs
- building and scaling LLM workflows (agents, pipelines, RAG)
- handling real-world issues like latency, reliability, and hallucination control
- integrating AI into product experiences end-to-end
Looking for engineers who:
- have built production systems (not just prototypes)
- are strong on backend design and data flow
- have experience with AI/LLM systems in real use cases
Remote, async-friendly, with some overlap with US timezones preferred.
Hi! Saw your HN post. I build exactly this: production FastAPI+LangGraph RAG pipelines with self-correcting loops, pgvector search, and Redis streaming—deployed on AWS. My LinkedOut project is a multi-agent system handling 100+ concurrent tasks. Would love to share my GitHub. Available immediately!
We’re working on building production AI systems , not demos ,focused on real-world workflows, data pipelines, and integrating LLM-based systems into usable products.
Stack: - Python (FastAPI) - React / TypeScript - AWS / PostgreSQL
Work includes: - designing backend systems and APIs - building and scaling LLM workflows (agents, pipelines, RAG) - handling real-world issues like latency, reliability, and hallucination control - integrating AI into product experiences end-to-end
Looking for engineers who: - have built production systems (not just prototypes) - are strong on backend design and data flow - have experience with AI/LLM systems in real use cases
Remote, async-friendly, with some overlap with US timezones preferred.
If interested, apply here: https://lnkd.in/dbiCSZhW
Make sure to check your email (including spam/junk), as that’s required to move forward in the process.