Experteer Overview
¿Es este el siguiente paso en su carrera? Descubra si es el candidato adecuado leyendo la descripción completa a continuación.
In this role you lead backend engineering for the AI & Knowledge Search platform, driving scalable, reliable systems that empower employees and AI builders. You own the architecture, guide vendor work, and implement RAG-based solutions to accelerate knowledge access. You will mentor a distributed engineering team and shape technical direction in an instruction-free agile environment. This is a chance to impact how knowledge is retrieved and applied across the company, using Python, AWS, and Generative AI.
Compensaciones / Beneficios
• Act as the primary System Lead, maintaining lifecycle docs and environments (Dev/QA/Prod) while conforming to ITIL and BI architecture standards
• Set up AI evaluation and monitoring frameworks (e.g., Langfuse) to measure model performance and reliability
• Design and implement Retrieval-Augmented Generation (RAG) and agentic systems for faster, more accurate knowledge search
• Develop high-quality Python services with emphasis on modularity, testability, and code quality (type hints, PyTest, Pydantic)
• Build robust data pipelines for unstructured data using Docling, AWS Glue, and Apache Airflow to feed AI models
• Coordinate enterprise-wide integrations using platforms like SnapLogic
• Manage AWS cloud infrastructure (ECS, EC2, VPC, Lambda) and containerized workloads (Docker); own CI/CD processes
• Provide technical leadership to external vendor teams, align deliverables with architecture, and internalize knowledge for team use
Responsabilidades
• Bachelor’s or Master’s degree in Computer Science, Engineering, or related field
• 8+ years backend engineering with full-stack experience, strong system integration and ownership
• 2+ years leading a team of engineers; experience with external vendors is a plus
• Deep software engineering fundamentals, modularity, testability, and architectural patterns for complex data workflows xpzdshu
• Experience designing RAG architectures and Agentic Workflows; familiarity with LangChain, LlamaIndex, vector databases (Pinecone, Milvus, or Chroma)
• Proficiency in AWS cloud infrastructure (ECS, EC2, VPC, Lambda) and Infrastructure as Code (Terraform, CloudFormation, or AWS CDK)
• Strong autonomy and stakeholder management skills; ability to translate sprint goals into technical requirements; documentation discipline
Requisitos principales
• Flexible working conditions
• Life and accident insurance
• Health insurance at a competitive price
• Investment in learning and development
• Gym membership discounts