Senior AI Engineer

This is a fully remote position, open to applicants in Brazil.

📋 Description

• Design, create, and sustain production-grade LLM integration pipelines, including retrieval-augmented generation (RAG), prompt engineering, output parsing, and chain orchestration.

• Develop and manage AI functionalities within Jeeves's 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 to guarantee that AI decisions adhere to reliability standards for financial applications.

• Assess and incorporate AI frameworks and tools (LangChain, LlamaIndex, OpenAI API, Anthropic API, HuggingFace, vector databases) and advocate for the most suitable tool for each task.

• Establish practices for prompt versioning and evaluation to maintain the accuracy and consistency of AI outputs as models and data change.

• Design and uphold vector search pipelines utilizing databases such as Pinecone, Weaviate, or pgvector to enhance semantic search and RAG-based features.

• Construct document ingestion and chunking pipelines for Jeeves's financial data, processing invoices, receipts, policy documents, and transaction records.

• Improve retrieval quality through the selection of embedding models, chunk strategies, metadata filtering, and re-ranking techniques.

• Collaborate with data scientists to transition trained ML models from experimental notebooks to production-serving infrastructure.

• Create and maintain model serving endpoints with appropriate latency service level objectives (SLOs), input validation, and output monitoring.

• Implement model performance monitoring and data drift detection to ensure the ongoing accuracy of production models.

• Support model retraining workflows by designing clean data pipelines and feature engineering that can be updated continuously.

• Seamlessly integrate AI services with Jeeves's backend microservices, designing clear API contracts, circuit breakers, and graceful degradation patterns.

• Write high-quality, testable backend code in Python or Go/Node.js to enable AI-integrated features.

• Instrument AI components with structured logging, distributed tracing, latency dashboards, and alerting to ensure operational visibility.

• Build human-in-the-loop review workflows for AI decisions requiring oversight, especially for high-value financial actions.

• Collaborate with Product, Backend Engineering, and Data Science teams to define the AI roadmap and translate requirements into dependable systems.

• Contribute to a culture of quality by drafting design documents, reviewing AI system designs from peers, and sharing insights openly.

• Assist in expanding the AI engineering practice at Jeeves by establishing patterns, tools, and best practices for the broader team to utilize.

⛳️ Requirements

• Bachelor's degree in Computer Science, Engineering, or a related field, or equivalent practical experience.

• Over 5 years of professional software engineering experience, with at least 3 years dedicated to AI/ML systems in production.

• Practical experience in building and deploying LLM-powered applications using APIs such as OpenAI, Anthropic, or Cohere in a production context.

• Experience in designing and managing RAG pipelines, including chunking strategies, embedding models, and vector database integration (Pinecone, Weaviate, pgvector, or similar).

• Strong proficiency in Python for AI/ML workloads; familiarity with at least one AI orchestration framework (LangChain, LlamaIndex, or equivalent).

• Experience with ML model serving infrastructure, including REST or gRPC inference endpoints, input/output validation, latency budgeting, and monitoring.

• Solid backend engineering fundamentals, including REST APIs, relational databases (PostgreSQL preferred), asynchronous patterns, and cloud infrastructure (AWS, GCP, or Azure).

• Experience with observability tools, including structured logging, distributed tracing, and creating dashboards for AI system health.

• Preferred Qualifications: Experience in fintech, financial services, or regulated industries where AI reliability and auditability are essential.

• Familiarity with prompt evaluation frameworks, A/B testing of AI outputs, and monitoring model performance degradation in production.

• Experience with ML lifecycle management tools, such as MLflow, Weights & Biases, Vertex AI, or SageMaker.

• Knowledge of real-time data streaming (Kafka, Kinesis) for event-driven AI pipelines.

• Contributions to open-source AI tools, published technical writing, or presentations at AI/ML conferences.

• Prior experience in startups or scale-ups, with comfort in ambiguity and building foundational systems from the ground up.

🏝️ Benefits

• This is a full-time remote position.