7 months ago
Remote, IndiaSenior
Responsibilities
- Design, build, and maintain production-grade LLM integration pipelines using RAG, prompt engineering, output parsing, and chain orchestration.
- Develop AI features for spend categorization, document extraction, anomaly detection, financial Q&A, and automated reconciliation.
- Implement structured output validation, fallback handling, confidence scoring, prompt versioning, and AI output evaluation practices.
- Build vector search, document ingestion, chunking, embedding, metadata filtering, and re-ranking pipelines.
- Collaborate with data scientists to productionize ML models and build serving endpoints with validation, latency targets, monitoring, and drift detection.
- Integrate AI services with backend microservices and implement API contracts, circuit breakers, graceful degradation, logging, tracing, dashboards, and alerting.
- Build human-in-the-loop workflows for AI decisions requiring oversight.
- Partner with Product, Backend Engineering, and Data Science on the AI roadmap and help establish AI engineering practices.
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.
- Production experience building and deploying LLM-powered applications using APIs such as OpenAI, Anthropic, or Cohere.
- Experience designing and operating RAG pipelines with chunking strategies, embedding models, and vector databases.
- Strong Python proficiency and familiarity with an AI orchestration framework such as LangChain or LlamaIndex.
- Experience with ML model serving infrastructure, inference endpoints, input/output validation, latency budgeting, and monitoring.
- Backend engineering experience with REST APIs, relational databases, asynchronous patterns, and cloud infrastructure.
- Experience with structured logging, distributed tracing, and dashboards for AI system health.
- Preferred experience includes fintech or regulated-industry work, prompt evaluation, A/B testing AI outputs, production model monitoring, ML lifecycle tools, real-time streaming, open-source AI contributions, technical writing, conference talks, and startup or scale-up experience.
Benefits
- Full-time remote position.
- Opportunity to build foundational AI systems for a global financial technology platform.
Tech Stack
Categories
About Jeeves
Jeeves builds a finance platform for global businesses, combining multi-currency accounts, corporate cards, cross-border payments, and spend management in one system. The privately held company is headquartered in Miami and operates in 20+ countries across the Americas, the United Kingdom, and Europe, serving over 5,000 clients ranging from venture-backed startups to SMBs.