Senior Development Lead – AI, RAG Platform

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

📋 Description

• Take the lead in the hands-on development of the AI Extraction Gateway, evolving from Simple RAG to Complex RAG.

• Implement and optimize the expert-weighted (SME) retrieval layer along with structured result validation.

• Oversee the calibration of confidence scores; work in partnership with the BA on accuracy rubrics and testing evidence.

• Propel the technical delivery rhythm through sprint planning, code evaluations, identification of technical risks, and facilitating team progress.

• Ensure consistent application of architectural patterns throughout the codebase.

• Collaborate with the Data Engineer on integrating ingestion pipeline connection points and the vector store schema.

• Develop and refine the query orchestration layer using Python/FastAPI, AWS Lambda/ECS.

• Assist the QA Automation Engineer in creating the validation harness for RAG outputs.

• Maintain observability in development through structured logging, CloudWatch dashboards, and X-Ray tracing.

⛳️ Requirements

• Over 6 years of experience in software development, with at least 2 years in a tech lead or senior engineering lead role.

• Proficient in Python development; experience with FastAPI or an equivalent asynchronous Python framework is essential.

• Practical AWS experience, including ECS and/or Lambda, API Gateway, DynamoDB, S3, CloudWatch, and X-Ray.

• Familiarity with vector databases such as OpenSearch, Pinecone, Weaviate, or similar technologies.

• Strong grasp of API design, service decomposition, and clean backend architecture.

• AI experience is mandatory (not optional).

• Successfully delivered at least one production-grade RAG, semantic search, or LLM-integrated application from start to finish, rather than a prototype or internal tool.

• Hands-on experience integrating with LLM provider APIs (such as OpenAI, Anthropic, or Amazon Bedrock) in a production or enterprise setting.

• Knowledge of chunking strategies, embedding models, retrieval ranking, and prompt engineering within a production environment.

• Experience in confidence scoring, retrieval evaluation, or approaches to mitigate hallucination in a deployed system.

🏝️ Benefits

• Options for remote work.