Zipporin is seeking a forward-thinking AI & Generative LLM Solutions Engineer to join our technical team in San Francisco, CA on a hybrid schedule. In this high-impact role, you will architect, implement, and deliver cutting-edge generative AI and large language model (LLM) applications for enterprise-grade deployments, turning state-of-the-art research into scalable, production-ready solutions.
Key Responsibilities:
- Architect and deploy production-grade Generative AI workflows, specialized agentic pipelines, and Retrieval-Augmented Generation (RAG) systems.
- Partner directly with enterprise stakeholders and product teams to translate complex business challenges into resilient LLM-powered technical architectures.
- Benchmark, optimize, and maintain vector search infrastructure, data indexing pipelines, and embedding models for low-latency retrieval.
- Conduct fine-tuning, quantization, and evaluation benchmarks across open-source and proprietary foundation models to optimize for accuracy, safety, and operational costs.
- Build robust observability, guardrails, and telemetry systems to continuously monitor model hallucination rates, latency, and drift.
Requirements:
- Bachelor’s or Master’s degree in Computer Science, Machine Learning, or equivalent practical experience.
- Demonstrated experience designing and deploying scalable Python-based backend systems and AI architectures.
- Hands-on expertise with modern Generative AI tooling, including LangChain, LlamaIndex, vLLM, and vector databases such as Pinecone, Qdrant, or Milvus.
- Strong grasp of foundation model architectures, context-window management, prompt engineering strategies, and LLM evaluation frameworks.
- Proven ability to bridge deep technical domain knowledge with client-facing consultative problem-solving.