Description

Design and own the end-to-end architecture for GenAI-powered product features, ensuring scalable, secure, and compliant solutions.

This role is hybrid.

Responsibilities

• Design and own the end-to-end architecture for GenAI-powered product features.
• Guide engineering teams on best practices for GenAI development, integration, and model adaptation.
• Establish standards and patterns for prompts, agents, and inference layers, including RAG and vector databases.
• Ensure security, compliance, and responsible AI principles are built into every solution.
• Translate product requirements into AI-driven capabilities and technical designs for customer-facing and internal products.

Required Skills

• 8+ years of experience in software architecture, ML engineering, or platform engineering.
• 2+ years of hands-on experience with AI/ML systems, including Generative AI.
• Strong software engineering background in Python, Java, or similar languages.
• Strong understanding of Generative AI models (LLMs, multimodal models, embeddings) and foundation models.
• Hands-on experience with prompt engineering, prompt orchestration, and agent-based frameworks.
• Experience with RAG architectures, vector databases, and multi-agent systems.
• Knowledge of low-latency inference, model routing, fallback strategies, and event-driven microservices.
• Background in data platforms, analytics engineering, or enterprise AI governance.

Preferred Skills

• Familiarity with open-source AI ecosystems and model adaptation techniques.
• Experience with A/B testing, feature flags, and iterative product releases involving AI.

Key Skills

Education

Bachelor's degree