Principal Engineer, Python fullstack (React+Genai)

Overview

Principal Engineer to design and deliver production-grade Generative AI and agentic AI solutions end-to-end, spanning backend LLM inference, RAG pipelines, and AI-native frontend experiences.

What you'll do

• Convert client business use cases and technical requirements into technical designs.
• Design scalable, secure, and cost-efficient backend platforms for LLM inference and RAG pipelines.
• Define frontend architecture and UX patterns for AI-native applications.
• Lead complex GenAI workflows combining LLMs, tools, APIs, structured data, and user context.
• Drive integration of AI/ML capabilities into products and establish engineering standards for prompt design and evaluation.
• Troubleshoot AI model and implementation issues and ensure documentation and observability.
• Conduct technical discovery, solutioning, design/code reviews, and POCs to validate technologies.

What you'll need

• Total experience: 11+ years.
• 10+ years in software engineering with strong depth in Python.
• Proficiency in React and modern frontend frameworks.
• Proven experience architecting and delivering Generative AI applications at scale.
• Experience designing and implementing ML/genAI/agentic AI models and algorithms.
• Hands-on experience with cloud platforms (AWS, Azure, or GCP) and distributed systems.
• Experience with security, privacy, and governance considerations for enterprise AI.

Details

• Expected to coordinate integration of RAG APIs and vector DB pipelines.
• Expected to integrate cloud with AI algorithms and on-premises AI algorithms.
• Expected to work in an agile methodology and manage delivery across pods building scalable AI and API services.
• Uses AI-assisted development tools (e.g., Copilot, Claude Code) while maintaining production-grade quality.
• Requires a Bachelor’s or master’s degree in computer science, Information Technology, or a related field.