The posting
Client: mid-size US startup (Series B, about 150 people) · Location: remote, LATAM, 4+ hours overlap with US Eastern · Level: mid Engagement: full-time contractor
You will ship LLM-powered features into a B2B SaaS product, working with product engineers from prototype to production.
What you will do
- Build retrieval-augmented generation pipelines and agent workflows on top of commercial and open-source LLMs
- Write and version prompts, tools and evaluation sets
- Integrate AI features into the product's Python and TypeScript services
- Measure quality, latency and cost, and improve them release over release
- Add guardrails, logging and tracing for production use
What you bring
- 3+ years of software engineering, at least 1 building LLM applications in production
- Strong Python; experience with an LLM framework or SDK (LangChain, LlamaIndex or direct provider APIs)
- Vector databases (pgvector, Pinecone or Weaviate) and embedding-based search
- API design, testing and CI/CD habits
- Advanced English
Nice to have
- Evaluation tooling (LangSmith, Braintrust, Ragas)
- TypeScript and React
- Fine-tuning or classical ML background



