LLM / GenAI Engineer

About The Role The role builds production-grade LLM and generative AI systems, including retrieval-augmented generation, tool-using agents, model adaptation, and evaluation infrastructure. The engineer will turn emerging foundation-model capabilities into reliable features with measurable gains in quality, latency, cost, and safety. The team works across applied research, backend engineering, and platform infrastructure to deploy AI systems used in real customer workflows. This role is based in Seattle, WA, with remote flexibility and requires strong ownership from technical design through production monitoring. Key Responsibilities Design and implement RAG and agentic workflows using Python, LangChain, LlamaIndex, or custom orchestration services Build ingestion, chunking, embedding, retrieval, reranking, and citation pipelines using vector stores such as pgvector, Pinecone, or Elasticsearch Develop evaluation systems with curated benchmark sets, LLM-as-judge workflows, human review, regression testing, and task-specific quality metrics Fine-tune and serve foundation models using supervised instruction tuning, LoRA or QLoRA, Hugging Face Transformers, and vLLM or equivalent inference stacks Optimize production inference for latency, throughput, and cost across hosted APIs and cloud GPU infrastructure Integrate model-powered services with backend systems through reliable APIs, asynchronous workflows, observability, guardrails, and fallback behavior Partner with product, data science, and infrastructure engineers to ship tested releases and monitor model quality, drift, safety, and operational health What We Are Looking For 3–8 years of experience in software engineering, machine learning engineering, applied research, or a related discipline, including at least 1 year delivering LLM or GenAI systems to production Strong Python skills with experience building maintainable services, asynchronous applications, REST APIs, and automated tests Hands-on experience with RAG, embeddings, vector databases, prompt and context design, structured generation, and LLM evaluation Proficiency with PyTorch and Hugging Face Transformers, plus practical experience with fine-tuning, quantization, batching, or GPU inference optimization Experience deploying AI workloads on AWS, GCP, or Azure using Docker, Kubernetes, CI/CD, and production monitoring tools Solid understanding of ML fundamentals, transformer architectures, retrieval quality, model failure modes, responsible AI, and security risks such as prompt injection and data leakage Bachelor’s or master’s degree in computer science, machine learning, electrical engineering, mathematics, or a related technical field; Bonus: experience with multimodal models, open-source model serving, distributed training, knowledge graphs, or ML platform development Show more Show less