AI Engineer
Take AI features from a prompt in a notebook to a reliable, evaluated product capability — and own the gap between a demo that impresses and a system that holds up.
- Remote · USA
- Full-time
- Senior · Engineering
About the role
We help clients put AI to work on real problems: retrieval over their own data, agents that take actions, automations that remove genuine operational drag. Most of the hard part is not the model — it is everything around it: grounding, evaluation, latency, cost, and failure modes.
As an AI Engineer, you own that surrounding system. You design the retrieval and prompting strategy, build the evaluation harness that tells us whether a change actually helped, and ship features that behave predictably for real users — not just in the happy-path demo.
This role is fully remote and open to candidates based in the United States. You will work directly with product and frontend engineers, and you will have the autonomy to choose the right approach for the problem in front of you.
What you'll do
- Design and ship LLM-powered features: retrieval-augmented generation, structured extraction, agents, and automations.
- Build evaluation harnesses and offline / online metrics so we can measure quality and catch regressions.
- Own the practical concerns — latency, cost, token budgets, caching, and graceful failure.
- Implement retrieval pipelines: chunking, embeddings, vector search, and re-ranking.
- Add observability and guardrails so AI behavior in production is visible and safe.
- Partner with engineers and clients to scope what AI should — and should not — be doing.
What we're looking for
- 4+ years of software engineering, with recent hands-on work shipping LLM-based features to production.
- Strong Python and / or TypeScript.
- Practical experience with the major model APIs (OpenAI, Anthropic) and prompt / context design.
- A rigorous, evals-first mindset — you do not trust a feature you cannot measure.
- Solid software fundamentals: APIs, data modeling, testing, and version control.
- Clear written communication and honesty about what AI can and cannot reliably do.
Nice to have
- Experience with RAG frameworks and vector databases (pgvector, Pinecone, Weaviate, and similar).
- Fine-tuning, function / tool calling, or multi-step agent orchestration in production.
- A background in ML / data science, or in classic backend systems at scale.
Stack & tools
- Python
- TypeScript
- OpenAI / Anthropic APIs
- RAG & vector search
- Evals & observability
- AWS
How to apply
To apply, send an email to hiring@logicleague.org with the subject line “Application: AI Engineer”. Tell us a little about yourself, attach your CV or portfolio, and link to anything you're proud of. A real person on our team reads every application and replies.