Mid-Senior AI Engineer
hace 1 día
Leeds
👋 About Renude Renude builds AI-powered software for the beauty industry, helping brands deliver personalised, expertise-focused customer support through intelligent digital agents. Our technology powers e-commerce experiences including: skin analysis, product recommendation and LLM-based chat. We’ve been awarded by CEW, Beauty Innovation Awards, Tech Nation and more. We have raised over $4M from leading tech investors in addition to being awarded Innovate UK Grants. Our team combines tech, formulation, dermatology, e-commerce and sales expertise. 🔧 What You'll Do We’re hiring a mid-senior (4+ years experience) AI Engineer to help design, build, and scale our production AI systems with ownership from design to deployment. You’ll work end-to-end across Agentic RAG conversational agents, Agent orchestration, fine-tuning models, retrieval pipelines, evaluation frameworks and generating product recommendation for real customer interactions to deliver reliable AI-powered experiences in production. • Design, build, and deploy Agentic AI workflows and RAG-powered applications for real-world use cases, • Develop scalable backend services and APIs powering AI agents and conversational systems, • Build and optimise retrieval pipelines including embeddings, chunking, reranking, memory and vector search, • Collaborate closely with product, design, and engineering teams to shape AI-first experiences, • Integrate LLM systems into user-facing web applications and product features, • Improve response quality, reliability, latency, observability and cost efficiency of production AI systems, • Evaluate new AI frameworks, tools, and orchestration approaches across the rapidly evolving LLM ecosystem, • Influence architecture decisions for scalable, secure, and production-ready AI infrastructure ✅ What We're Looking For Must-Haves: • Bachelor’s degree in Computer Science, Artificial Intelligence, Engineering, or equivalent practical experience, • 4+ years experience building and deploying production AI applications, • 2+ years experience developing LLM-powered products, conversational AI, RAG systems, or agentic workflows, • Strong Python skills and experience building backend systems and APIs, • Hands on experience building agentic workflows, tool-calling pipelines, and stateful orchestration using frameworks such as LangGraph, LangChain, LlamaIndex, AutoGen, CrewAI or similar agent orchestration frameworks, • Strong experience designing and optimising retrieval systems, including vector stores (Pinecone, Weaviate, Chroma), graph-based RAG architectures, hybrid retrieval, reranking, and semantic search pipelines, • Experience with production optimisation for RAG systems, including latency optimisation, token cost control, context management, monitoring, guardrails and prompt versioning, • Exposure to AIOps/MLOps practices and hands-on experience with AWS Bedrock, SageMaker, Vertex AI, or similar cloud AI platforms, • Comfortable working autonomously and taking ownership in a fast-moving, remote, startup environment Nice-to-Haves: • Masters or advanced degree in artificial intelligence, machine learning, natural language processing or related field, • Experience with LLM fine-tuning techniques such as LoRA, QLoRA, supervised fine-tuning (SFT), instruction tuning, and parameter-efficient model adaptation workflows, • Experience with evaluation and monitoring frameworks for LLM systems, including RAGAS, OpenEvals, DeepEval, LangSmith, OpenTelemetry or LLM-as-a-Judge evaluation frameworks, • Familiarity with graph databases such as Neo4j or Amazon Neptune, • Experience with recommendation systems, personalisation pipelines or ranking systems, • Experience building modern web applications using Django, FastAPI, React, or similar frameworks, • Comfortable using Docker and containerised development workflows, • Exposure to CI/CD pipelines, infrastructure-as-code, and cloud-native deployment practices 🌱 What We Offer • Competitive compensation (based on experience), • Remote-friendly culture with flexible working hours, • Opportunity to work with cutting edge technologies, • High ownership and real technical influence, • A supportive team that values product excellence and personal growth