- Professional
- Ufficio in New York
- Own the full lifecycle of AI-powered agents and workflows - from initial design through deployment - starting with existing solutions and evolving toward custom systems.
- Build and maintain data flows and retrieval infrastructure - including the Model Context Protocol - to transform raw business data into structured, policy-compliant formats and enable secure, semantic access across domains like sales, support, and product.
- Lead the evolution of the agent orchestration layer, enabling intelligent task routing across multiple LLMs/Agents to optimize scalability, cost, latency, and throughput in large-scale production AI systems.
- Implement observability and feedback mechanisms to measure agent performance, identify areas for optimization, capture trust signals, and guide continuous improvement.
- Contribute to the technical vision and the long term roadmap of foundational AI systems at Quantifi.
- Stay informed on emerging approaches in AI agent architectures, orchestration frameworks, and retrieval-augmented systems to continuously refine our platform design and strategy.
- You are motivated by building reliable systems that provide a strong foundation for future growth and take pride in designing solutions that are robust and sustainable.
- You stay current with emerging tools, frameworks, and best practices, and can identify and apply the right innovations in a practical, production-ready way.
- You work well in situations where requirements are not fully defined, bringing clarity to challenges, asking the right questions, and communicating your ideas clearly.
- You are a problem solver who can create a clear path forward without an established template, balancing strategic thinking with hands-on execution to deliver measurable value.
- Bachelor's degree in Computer Science, Engineering or a related field
- 3+ years of experience as a software or platform engineer, building and deploying production systems with Python, TypeScript, or Node.js.
- Solid understanding of AI/ML fundamentals, with hands-on experience using LLMs and building, deploying, and operating AI agents.
- Experience with data pipelines, retrieval systems, or other backend infrastructure that supports AI applications.
- Familiarity with distributed systems concepts (scalability, performance optimization, cost management), and AI-specific techniques including agent orchestration, prompt engineering, and intelligent routing logic.
- Ability to work across the full development lifecycle - from architecture and prototyping to deployment and monitoring - in a fast-moving environment.
- Strong problem-solving skills, with the ability to navigate ambiguity and adapt to evolving requirements.
- Experience with agent frameworks such as LangChain, LangGraph, or CrewAI
- Experience with Microsoft ecosystem tools, including C# and Azure AI services (e.g., Azure OpenAI, Copilot).
- Background with vector databases like Pinecone, Weaviate, Qdrant, or similar tools.
- Familiarity with Claude Enterprise or other secure LLM environments.
- Experience designing agent-based architectures or internal developer platforms.
- Exposure to RevOps, GTM tooling, or enterprise SaaS systems.
- Proficiency in additional backend languages such as Go or Java.
Salary: 180k – 200k