REQUIRED EXPERIENCE

5+ years shipping production software, with hands-on, production use of LLM-based development over the past year.
Strong TypeScript/React and Python or Node.js: production APIs, service design, webhooks, background processing.
Hands-on RAG, embeddings, and vector search, plus at least one agentic framework (LangGraph, Claude Agent SDK, or OpenAI Agents SDK).
Advanced PostgreSQL or comparable relational-database experience: schema design, migrations, audit models, tenant permissions.
Document processing (PDFs, OCR, extraction), keeping probabilistic extraction separate from deterministic decisioning logic.
Fluent Spanish and English; comfortable working directly with financial-services clients across Latin America.

KEY CAPABILITIES

Owns features end to end, from client conversation to production infrastructure.
Cares about evaluation and reliability, not just the happy path.
Client-facing mindset: translates business requirements into technical solutions.
Learns new tools and models fast, and shares what works.

Lead discovery with lending, credit, and insurance teams and map intake, underwriting, decisioning, and audit workflows into precise product requirements.
Design and build the agentic systems behind Weston's context layer — orchestration, tool and function calling, memory, and guardrails.
Build document-processing and extraction pipelines that turn borrower, policy, and credit-file documents into structured, decision-ready data.
Own components end to end: React front end, Python or Node services, RAG pipelines, and evals — and demo work frequently to gather feedback.
Find edge cases, conflicting requirements, and compliance concerns across regulated financial workflows before they become production problems.

THE AI CONTEXT LAYER FOR LATAM FINANCIAL SERVICE COMPANIES

Who Weston is

Weston builds the AI context layer that powers workflow automation for financial services institutions across Latin America. Our agents read documents, apply business rules, and move files across intake, underwriting, decisioning, and audit — turning mortgage, credit, and insurance workflows into agent-run, decision-ready processes that plug into how these institutions already operate.

Background in mortgage lending, consumer credit, insurance, or another regulated financial workflow.
Experience with MCP servers, multi-agent patterns, or LLM evaluation tooling (LangSmith, Langfuse, promptfoo).
Experience with Terraform, CI/CD pipelines, and cloud security or privacy practice (AWS, GCP, or Azure; IAM; PII safeguards).