TheCarSite - AI Engineer - LLM/Generative AI

About the Role : We are looking for an AI Engineer with hands-on experience in building and deploying AI-powered applications using Large Language Models (LLMs), Generative AI and modern AI frameworks. You will be responsible for designing, developing and integrating intelligent systems that solve real-world business problems through automation, conversational interfaces and AI-driven workflows. You will work closely with backend engineers, frontend engineers, product stakeholders and engineering leadership to take AI solutions from experimentation to production.Key Responsibilities : - Design, develop and deploy AI-powered applications using LLMs and Generative AI technologies.- Build intelligent AI agents capable of executing multi-step tasks and interacting with external systems.- Develop conversational AI solutions with context awareness, memory and natural language understanding.- Design and implement Retrieval-Augmented Generation (RAG) pipelines.- Integrate LLMs with external APIs, databases and third-party services.- Build agentic workflows using tool calling, function calling and orchestration frameworks.- Develop systems for processing, analysing and extracting insights from unstructured data.- Implement prompt engineering techniques and optimise model performance.- Evaluate AI outputs for accuracy, reliability, latency and cost.- Implement appropriate guardrails, error handling and fallback mechanisms.- Develop scalable APIs and services to integrate AI capabilities with existing applications.- Monitor, troubleshoot and continuously improve AI applications in production.- Stay up to date with emerging developments in LLMs, AI frameworks and agentic architectures.Required Skills : - 5 - 8 years of software engineering experience, with meaningful hands-on experience in AI/ML or Generative AI.- Experience with AI agent frameworks such as LangChain, LangGraph, LlamaIndex or similar.- Experience implementing MCP (Model Context Protocol) servers and clients.- Familiarity with multi-agent architectures and agent orchestration.- Strong programming experience in Python.- Practical experience working with LLM APIs such as OpenAI, Anthropic or Google Gemini.- Experience building applications using LLMs and Generative AI.- Understanding of prompt engineering, context management and token optimisation.- Hands-on experience with RAG architectures and vector databases.- Understanding of embeddings, semantic search and information retrieval.- Experience building REST APIs and integrating external services.- Familiarity with asynchronous programming and event-driven architectures.- Good understanding of software engineering principles, debugging and testing.Good to Have : - Experience taking applications from development to production.- Experience with vector databases such as Pinecone, Qdrant, Weaviate or pgvector.- Working knowledge of Node.js and TypeScript.- Familiarity with PostgreSQL and relational database concepts.- Experience with speech-to-text, text-to-speech and audio processing technologies.- Experience with conversational AI platforms and chatbot development.- Familiarity with Docker, AWS and cloud-based deployments.- Experience with LLM evaluation frameworks, observability and monitoring.- Exposure to open-source models and frameworks such as Hugging Face.What We're Looking For : - Strong problem-solving and analytical abilities.- A practical engineering mindset with a focus on building working solutions.- Ability to distinguish between problems that require AI and those better solved using conventional software engineering.- Comfortable experimenting with new technologies and translating prototypes into production-ready systems.- Ability to work independently and take end-to-end ownership.- Strong understanding of system design, scalability and reliability.- Ability to balance AI model quality, application performance and infrastructure costs.- Good communication and collaboration skills.- Comfortable working in a fast-moving product engineering environment.What We Offer : - Opportunity to build and deploy real-world AI-powered products.- Hands-on exposure to LLMs, Generative AI and agentic architectures.- Opportunity to experiment with emerging AI technologies and frameworks.- A small, collaborative engineering team with significant ownership.- Direct collaboration with engineering leadership and product stakeholders.- Opportunity to influence technical architecture and engineering decisions. (ref:hirist.tech)