Zipporin is seeking an experienced AI & Generative LLM Solutions Engineer to spearhead the design and delivery of cutting-edge generative AI architectures for enterprise clients. Based in our New York, NY office on a hybrid schedule, you will serve as the technical bridge between frontier foundation models and mission-critical production systems, turning ambitious AI concepts into scalable, robust realities.
Key Responsibilities:
- Architect, develop, and deploy enterprise-grade Generative AI applications, focusing on Retrieval-Augmented Generation (RAG) systems and agentic workflows.
- Partner with strategic stakeholders and enterprise engineering teams to translate complex business challenges into production-ready LLM solutions.
- Benchmark, optimize, and fine-tune both open-source and proprietary foundation models (e.g., GPT-4, Claude, LLaMA) for latency, token efficiency, and accuracy.
- Integrate advanced semantic search and embedding pipelines utilizing vector databases such as Pinecone, Milvus, or Weaviate.
- Implement LLM observability, automated evaluation frameworks, safety guardrails, and red-teaming protocols across production environments.
Qualifications & Requirements:
- Bachelor’s or Master’s degree in Computer Science, AI, Mathematics, or a related quantitative discipline.
- 4+ years of professional software development experience, with deep expertise in Python and API development.
- Proven track record building and shipping applications powered by LLMs using frameworks such as LangChain, LlamaIndex, or AutoGen.
- Experience with cloud native services (AWS, GCP, or Azure), containerization (Docker, Kubernetes), and modern MLOps/LLMOps tools.
- Exceptional consultative and communication skills, with demonstrated ability to lead technical discovery sessions and present proofs-of-concept to executive audiences.