LLM / GenAI Engineer

About The Role The LLM / GenAI Engineer will build production AI systems that combine foundation models, retrieval, tool use, and structured data to solve high-value product and operational problems. The role spans experimentation and engineering: designing prompt and model strategies, building reliable inference services, and turning prototypes into scalable systems with measurable quality, latency, and cost targets. The engineer will partner with applied scientists, backend engineers, product teams, and platform specialists to develop RAG applications, agentic workflows, fine-tuning pipelines, and evaluation infrastructure. The work directly shapes how generative AI is deployed safely and reliably in customer-facing products. Key Responsibilities Design and implement production-grade RAG pipelines using Python, LangChain, LlamaIndex, or custom orchestration services Build retrieval systems with embedding models, hybrid search, reranking, and vector databases such as Pinecone, Weaviate, Elasticsearch, or pgvector Develop agentic workflows that integrate LLMs with internal APIs, tools, business rules, and structured data while handling failure modes and permissions Create systematic evaluation frameworks covering offline benchmarks, LLM-as-judge workflows, human feedback, regression testing, and production quality monitoring Fine-tune and optimize open-source or hosted models using instruction tuning, LoRA, QLoRA, quantization, batching, and inference optimization techniques Deploy observable AI services on AWS, GCP, or Azure using Docker, Kubernetes, CI/CD, and scalable inference APIs Establish safeguards for prompt injection, hallucination, sensitive data exposure, and unsafe or unauthorized tool execution What We Are Looking For 3–8 years of experience in software engineering, machine learning engineering, or applied AI, including at least 1 year building LLM-enabled systems in production Advanced Python skills with experience designing APIs, asynchronous services, testing strategies, and maintainable production code Hands-on experience with LLM application frameworks such as LangChain, LlamaIndex, Semantic Kernel, or equivalent custom architectures Strong understanding of embeddings, transformer models, tokenization, context windows, retrieval quality, prompt design, and model evaluation Experience deploying cloud-based AI workloads using Docker, Kubernetes, serverless infrastructure, or managed services such as AWS Bedrock, SageMaker, Vertex AI, or Azure OpenAI Proficiency with data and platform technologies including SQL, REST APIs, observability tooling, vector databases, and CI/CD pipelines Bonus: Experience with open-source model serving using vLLM or Text Generation Inference, multimodal models, distributed training, preference optimization, or security testing for AI systems; bachelor's or master's degree in computer science, machine learning, or a related technical field preferred Show more Show less