AWSCloudPythonAINLPNatural Language ProcessingGenerative AIClaudeGeminiRAGLangChainAutoGenLangGraphECSCI/CD
About this role
Role Overview
Define the long-term architectural vision and AI engineering standards for high-criticality systemic products.
Lead the evangelization, design, and structuring of a cross-team ecosystem for native AI development, including scalable practices for SDD (Spec-Driven Development), Intent Development, and Harness Engineering.
Ensure technical and economic governance of AI models, balancing token costs, latency, security (corporate guardrails), and data privacy.
Requirements
Proven experience in generative AI, LLMs (Claude, GPT, Gemini, etc.), virtual assistant development, and natural language processing (NLP).
Hands-on experience with vector databases, embeddings, RAG (including GraphRAG), prompt engineering, and context engineering.
Experience orchestrating agents using code-first frameworks (LangGraph, LangChain, Semantic Kernel, Strands, CrewAI, Autogen, or similar), building multi-step/multi-agent workflows with function calling and structured outputs.
Strong backend development experience (Python or similar), microservices, event-driven architectures, AWS cloud governance (ECS, security, observability), and advanced model benchmarking/monitoring.
Experience designing and developing internal AI engineering frameworks, libraries, or platforms for use by other teams.
Mastery of code-agent-assisted workflows, standardization of Agent Skills, SDD (Spec-Driven Development), and Intent Development as robust architectural contracts interpretable by autonomous agents.
Ability to design platform-level Harness Engineering infrastructures, including CI/CD pipelines for continuous semantic validation of coding agents.
Tech Stack
AWS
Cloud
Python
Benefits
We value the continuous growth of zuppers, encouraging each person to pursue paths that drive their professional development.