Jeeves

Jeeves

Jeeves is a global financial infrastructure company that offers open business accounts, corporate cards, cross-border payments, and expense management through a borderless platform. With operations in 25+ countries, Jeeves simplifies and centralizes fi...

Diversified Financial Services
251-1K
$368M raised

Description

  • Design, build, and maintain production-grade LLM pipelines, including RAG, prompt engineering, output parsing, and chain orchestration.
  • Develop AI features for core financial products such as spend categorization, document extraction, anomaly detection, financial Q&A, and automated reconciliation.
  • Implement structured output validation, fallback handling, and confidence scoring for financial AI use cases.
  • Evaluate and integrate AI frameworks and tools, and choose the most appropriate tools for each use case.
  • Establish prompt versioning and evaluation practices to keep AI outputs accurate and consistent over time.
  • Design and maintain vector search pipelines and document ingestion workflows for financial documents and transaction records.
  • Optimize retrieval quality through embedding selection, chunking strategy, metadata filtering, and re-ranking techniques.
  • Collaborate with data scientists to productionize ML models and build serving infrastructure with monitoring and latency controls.
  • Integrate AI services with backend microservices, including API contracts, circuit breakers, and graceful degradation patterns.
  • Instrument AI systems with logging, tracing, dashboards, and alerting, and build human-in-the-loop review workflows for sensitive decisions.

Requirements

  • Bachelor’s degree in Computer Science, Engineering, or a related field, or equivalent practical experience.
  • 5+ years of professional software engineering experience, including at least 3 years focused on AI/ML systems in production.
  • Hands-on experience building and deploying LLM-powered applications using APIs such as OpenAI, Anthropic, or Cohere.
  • Experience designing and operating RAG pipelines, including chunking strategies, embedding models, and vector database integration.
  • Strong proficiency in Python for AI/ML workloads.
  • Familiarity with at least one AI orchestration framework such as LangChain or LlamaIndex.
  • Experience with ML model serving infrastructure, including REST or gRPC inference endpoints, validation, latency budgeting, and monitoring.
  • Solid backend engineering experience with REST APIs, PostgreSQL or other relational databases, async patterns, and cloud infrastructure such as AWS, GCP, or Azure.
  • Experience with observability tooling such as structured logging, distributed tracing, and dashboards for AI system health.
  • Preferred: experience in fintech, financial services, or another regulated industry where AI reliability and auditability matter.
  • Preferred: familiarity with prompt evaluation frameworks, A/B testing AI outputs, and tracking production model degradation.
  • Preferred: experience with ML lifecycle management tools such as MLflow, Weights & Biases, Vertex AI, or SageMaker.
  • Preferred: knowledge of real-time data streaming tools such as Kafka or Kinesis.
  • Preferred: contributions to open-source AI tooling, technical writing, or conference talks in AI/ML.
  • Preferred: prior startup or scale-up experience and comfort building foundational systems in ambiguity.

Benefits

  • Full-time remote position.
  • Opportunity to work on AI systems embedded in real financial products used by businesses globally.
  • High ownership role shaping how Jeeves builds with AI as the company scales.
  • Work alongside backend engineers, data scientists, and product teams on production systems.
  • Backed by well-known investors and a well-funded company environment.
  • Exposure to a fast-growing, cross-functional engineering organization.
  • Chance to contribute to AI engineering standards, tooling, and best practices at the company.

Interested in this position?

Apply directly on the company website

Apply Now

Similar Roles

Senior Software Engineer I- (Forward Deployed AI)

Aledade 1K-5K Health Care Providers & Services

Aledade’s AI Enablement team is hiring a Senior Software Engineer I to work remotely with internal product, tech, and analytics teams to accelerate adoption of developer-centric AI tools and turn team-specific solutions into reusable platform patterns.

AWS CI/CD Databricks Datadog FastAPI Go GraphQL HIPAA JIRA Microservices Node.js OAuth PostgreSQL Python REST API Salesforce Snowflake TypeScript Vue.js
53 minutes ago

AI Engineer (Contract role)

AND Digital 1K-5K Internet Software & Services

AND Digital is hiring a contract AI Engineer to join its Customer Service Transformation Programme, building customer-facing agentic AI and agent workspace features within an AI & Agents squad.

AWS OpenAPI Python TypeScript
1 hour, 23 minutes ago

Agentic AI Solutions Architect - Remote, Latin America

Bluelight Consulting 11-50 Internet Software & Services

Bluelight is hiring a remote Agentic AI Solutions Architect in Latin America to lead client-facing AI strategy and design end-to-end agentic workflows that move from discovery through production deployment.

Apache Airflow AWS Azure GCP Generative AI LLM MLOps Prefect Python Snowflake SQL
1 hour, 45 minutes ago

Agentic AI Solutions Architect - Remote, Latin America

Bluelight Consulting 11-50 Internet Software & Services

Bluelight is hiring a remote Agentic AI Solutions Architect in Latin America to lead client-facing AI strategy and deliver end-to-end agentic automation and data solutions from discovery through production deployment.

Apache Airflow AWS Azure GCP Generative AI LLM MLOps Prefect Python Snowflake SQL
1 hour, 58 minutes ago

You're on a roll! Sign up now to keep applying.

Sign Up

Already have an account? Log in

Used by 14,729+ remote workers