Zipporin is seeking a forward-thinking AI & Generative LLM Solutions Engineer to join our team in New York, NY on a hybrid basis. In this role, you will bridge cutting-edge artificial intelligence research and enterprise-scale software engineering, architecting tailored generative AI and LLM implementations for high-impact business applications.
Key Responsibilities:
- Design, architect, and deploy production-ready LLM solutions, including advanced Retrieval-Augmented Generation (RAG) workflows and autonomous agentic systems.
- Partner directly with client executives and technical stakeholders to translate complex business objectives into scalable, secure AI architectures.
- Evaluate, benchmark, and fine-tune proprietary and open-source foundation models for cost, performance, latency, and domain accuracy.
- Implement robust guardrails, governance frameworks, and automated evaluation metrics to ensure model safety, reliability, and compliance.
- Lead technical proof-of-concepts (PoCs) through to full production deployment, mentoring engineering teams on Generative AI best practices.
Requirements:
- 5+ years of software engineering or solutions architecture experience, with at least 2+ years dedicated to building and deploying LLM applications in production.
- Deep technical fluency in Python and modern AI orchestration frameworks such as LangChain, LlamaIndex, or Semantic Kernel.
- Hands-on experience with vector search systems (e.g., Pinecone, Weaviate, Milvus, pgvector) and enterprise cloud infrastructure (AWS, GCP, or Azure).
- Proven ability to communicate sophisticated technical architectures effectively to both C-suite executives and engineering teams.
- Ability to work on-site in a hybrid capacity at our New York, NY office.