Jeeves
Jeeves
Jeeves is a financial platform that helps companies manage international spending and payments in one place. Its services include corporate card issuance, expense management, cross-border transfers, foreign exchange, and direct accounting integrations, supporting operations across more than 25 countries and multiple currencies. By bringing these functions together, Jeeves helps businesses reduce reliance on fragmented financial tools and improve day-to-day finance operations. The company is not a bank; it works with licensed banks and other financial institutions to provide its services.

Senior AI Engineer, Remote in Argentina

Lead production LLM workflows for Jeeves’ stablecoin banking platform, building AI systems that automate finance operations. Develop, evaluate, and monitor tools that support financial decisions.

Description

  • Lead finance workflows from initial problem definition through production and continuous improvement.
  • Design agentic and LLM systems that combine extraction, retrieval, reasoning, and tool use, with human review for high-value financial decisions.
  • Document system designs, choose whether to build or buy and which models to use, and define workflow success metrics.
  • Work directly with customers and internal finance teams to understand workflow needs and set completion criteria.
  • Build production-ready LLM pipelines with prompt and context design, structured outputs, validation, fallbacks, and confidence scoring.
  • Design retrieval and RAG components, including chunking, embeddings, vector search, and reranking.
  • Connect AI services to Jeeves’ backend through API contracts, retries, graceful degradation, and customer-level data isolation.
  • Manage model costs and response times.
  • Create evaluation datasets and automated tests, and identify regressions when prompts, models, or data change.
  • Add logging, tracing, dashboards, and alerts to AI components.
  • Maintain records of AI decisions for a regulated financial product.
  • Set shared patterns, tools, and practices for AI engineering.
  • Show the wider team effective ways to use coding agents and other AI tools.
  • Review AI system designs and share lessons learned.

Requirements

  • Bring at least seven years of professional software engineering experience, including two or more years building and operating production LLM or AI systems.
  • Have owned a substantial system or workflow from scoping and design through launch and iteration, with little oversight.
  • Have hands-on experience shipping LLM applications using Anthropic, OpenAI, or similar APIs, including structured outputs, error handling, and evaluation.
  • Have designed agentic or multi-step AI workflows with tool use, orchestration, or human review, or RAG systems using vector databases such as pgvector, Pinecone, or Weaviate.
  • Be proficient in Python and strong in backend fundamentals, including REST APIs, PostgreSQL or a comparable relational database, asynchronous patterns, and a major cloud platform such as AWS, GCP, or Azure.
  • Regularly use AI coding tools such as Claude Code, Cursor, or Codex, and be able to explain their strengths and limitations.
  • Have experience monitoring AI systems through logging, tracing, dashboards, and quality metrics.
  • Be professionally fluent in spoken and written English.

Related Jobs

Kreato Global | BPO and Language Solutions

Remote English-Spanish OPI/VRI Interpreter

Kreato Global | BPO and Language Solutions
201 – 500 Employees
HealthcareHospitalityLogistics

Interpret remotely between English- and Spanish-speaking people in medical, financial, social service, and customer care settings. Provide language support for Kreato Global across Latin America.

Open
SPERTON - Where Great People Meet

Sales Executive, Elevators and Car Parking Systems

SPERTON - Where Great People Meet
51 – 200 Employees

Drive elevator and car parking system sales across Mumbai’s Western Region. Build client and dealer relationships, and manage deals from initial enquiry through project execution.

Open