Ai engineer

Job Title: AI Engineer Location: Remote Type : Full-time About Us Oraion is your single source of truth for enterprise data. Oraion uses agentic AI to turn structured and unstructured enterprise data into non-obvious insights, instantly. Oraion helps you make faster, more informed decisions and even automate complex tasks, all through a self-serve, chat-based AI agent embedded in your existing workflow such as Slack, Teams or via our Enterprise Intelligence Platform. We’re looking for an AI Engineer to help us push the boundaries of intelligent agents in real-world enterprise environments. You’ll build robust, production-grade agentic and machine learning systems that connect insights to action. About the Role As an AI Engineer at Oraion, you’ll work across the full lifecycle of AI systems—from fine-tuning open source models and prompt engineering to agent orchestration and performance monitoring. You’ll be instrumental in shaping how our agents interact with enterprise data, uncover insights, and automate analysis within a secure and scalable infrastructure. This is a hands-on role with a strong engineering core. You’ll partner closely with data engineers, product managers, and UX designers to bring agent capabilities into our multi-tenant Saa S application, focusing on performance, reliability, and measurable value to the end user. Responsibilities Design, build, and deploy production-grade agentic AI systems using frameworks like Lang Chain, Lang Graph, and Lang Smith Implement scalable Retrieval-Augmented Generation (RAG) pipelines, including embedding strategies, vector DB integration, and query optimisation Fine-tune and evaluate LLMs for enterprise-specific tasks including summarisation, classification, clustering, and conversational reasoning Develop and maintain ML pipelines for NLP tasks such as sentiment analysis, topic modeling, and document clustering Continuously monitor and evaluate agent behaviour in production, using agent evaluation frameworks and performance metrics Integrate agents with internal systems via Model Context Protocol (MCP) or similar communication standards Collaborate with backend and data engineering teams to ensure seamless integration of AI components into our data platform Optimise AI workflows for latency, accuracy, and cost in a multi-tenant, high-scale environment Participate in the research and adoption of emerging tools, models, and frameworks to maintain a cutting-edge stack Requirements 1.5+ years experience with LLM’s and Agentic systems and 3+ years  experience in AI/ML engineering or backend engineering roles. Deep understanding of agentic architectures and experience deploying AI agents to production Expertise with Lang Chain, Lang Graph, Lang Smith or similar tools for orchestrating agents Strong practical experience with RAG systems and vector databases. Experience building and monitoring ML models in production environments (ML Ops experience) Skilled in LLM fine-tuning and prompt engineering for domain-specific tasks Proficient in unsupervised learning techniques for clustering, categorisation, and discovery Familiarity with Model Context Protocol (MCP) or similar standards for agent-system integration Strong coding skills in Python (and optionally Rust), with API development experience Experience working with multi-tenant Saa S applications and secure enterprise data environments Startup experience or a bias for fast, iterative delivery is a plus Bonus Points Experience integrating agents into messaging platforms (Slack, Teams, etc.) Knowledge of enterprise-grade data governance and access controls (e.g. ABAC) Previous work with real-time data workflows and streaming architectures Exposure to knowledge graphs or metadata-driven reasoning systems Familiarity with tools like Dagster, dbt, and Apache Iceberg in the broader data stack What We Offer Ground-floor opportunity to shape agentic AI at a fast-growing startup Collaborative team with deep experience across data, product, and AI Competitive compensation Remote-friendly, flexible working culture Access to cutting-edge LLMs, tools, and a forward-thinking product vision