About the CompanyOur client is a technology services company focused on helping organizations integrate artificial intelligence into their operations.The core offering is the design and implementation of AI-powered agents and automation systems that enhance productivity, decision-making, and operational efficiency.They work with companies across industries to deploy AI solutions that connect large language models, data systems, and internal tools into intelligent workflows.About the RoleWe are looking for a skilled AI Engineer to design, build, and deploy AI-powered agents and automation systems for our clients.In this role, you will work closely with product teams and client stakeholders to translate business needs into scalable AI solutions using modern AI frameworks and APIs.This position combines software engineering, AI system design, and client-facing technical implementation.Key ResponsibilitiesBuild AI Agents and Automation Systems: Design and implement intelligent agents powered by large language models capable of performing business tasks such as: research and data analysis; internal process automation; customer support workflows; document analysis and summarization; integrations with enterprise tools.Develop AI Applications: Build production-ready AI applications using modern frameworks such as: LangChain and LlamaIndex.Integrating models from providers such as: OpenAI and Anthropic.Implement Retrieval and Knowledge Systems: Design RAG (Retrieval-Augmented Generation) architectures that allow AI agents to retrieve and reason over internal company data.Design scalable AI system architectures including RAG pipelines, agent orchestration, and tool integrations.Integrate AI With Business Systems: Develop integrations with external tools and platforms such as: CRMs, databases, internal APIs, messaging systems, productivity tools, to enable AI agents to operate within real workflows.Rapid Prototyping and Iteration: Work in fast cycles to prototype, test, and iterate AI solutions in collaboration with internal teams and clients.Optimize AI Performance: Improve the reliability and performance of AI systems by: refining prompts, optimizing context management, evaluating model outputs, implementing evaluation pipelines and monitoring systems to ensure reliability and accuracy of AI outputs.Prompt engineering: Design and optimize prompts, tool use, and context management strategies for LLM-based systems.Required QualificationsBachelor’s degree in Computer Science, Engineering, or related field (or equivalent experience).5+ years of software engineering or AI development experience.Strong programming skills in Python.Experience building AI-powered applications using LLM APIs.Experience working with frameworks such as: LangChain, LlamaIndexExperience integrating APIs and external services.Familiarity with databases (SQL or NoSQL).Strong problem-solving and system design skills.Ability to work independently in a remote environment.Preferred SkillsExperience building AI agents or autonomous workflows.Experience deploying AI applications in cloud environments such as: Amazon Web Services, Google Cloud, Microsoft AzureFamiliarity with vector databases such as: Pinecone, WeaviateExperience with evaluation frameworks for LLM systems.Experience building scalable backend systems.Why Join The TeamWork on cutting-edge AI technologiesBuild solutions used by real businessesCollaborate with a global teamFully remote work environmentOpportunity to shape how organizations adopt AI agents.
#J-18808-Ljbffr