Our team is expanding, and we're bringing on a Solution Architect with deep specialization in Python and Generative AI to build and deliver enterprise-grade GenAI solutions ready for real-world production use. You'll be an integral part of our Solution Architecture group, spearheading technical exploration efforts, crafting reusable frameworks, and shaping standards for LLM-based applications. Submit your application to take part in forward-thinking GenAI initiatives and empower clients to achieve breakthrough outcomes.
Responsibilities
• Architect complete GenAI systems, including RAG frameworks, Agents, and Multi-Agent configurations, tailored for enterprise-level clients
• Develop reusable accelerators and reference builds to bring consistency to delivery approaches
• Facilitate technical discovery workshops while offering direct, practical support to engineering teams
• Establish evaluation methodologies and set standards for building large language model (LLM) applications
• Work alongside diverse teams to guarantee system designs that scale effectively and remain easy to maintain
• Build out microservices-based architectures leveraging established design patterns and contemporary frameworks
• Manage the incorporation of cloud infrastructure elements across platforms like AWS, Azure, or GCP
• Handle containerization and orchestration processes utilizing Docker and Kubernetes
• Assess and choose suitable vector database solutions, such as Pinecone, Weaviate, or Chroma, for GenAI use cases
• Deploy LLMOps methodologies and monitoring solutions to fine-tune production-level deployments
• Assist with prompt management and RAG evaluation processes to boost application precision
• Take part in mentoring efforts and knowledge exchange across the broader architecture team
• Maintain high standards of production-ready code quality within Python-based applications
• Push forward ongoing enhancements in system architecture and solution scalability