Generative AI Engineer

Tenth Revolution Group; Wes-Kaap; On-site; ZAR 700,000 - 1,100,000; Full time

Job summary

Tenth Revolution Group seeks an Advanced LLM & Agent Engineering specialist to design, develop and deploy production-grade LLM applications and autonomous agent systems, including multi-agent architectures, tool calling, agent memory and orchestration.

You will evaluate models from OpenAI, Anthropic, Google and Meta, lead architectural decisions on hosted vs self-hosted inference and RAG, and drive production readiness, monitoring and governance across the AI lifecycle while collaborating with

Job description

• Advanced LLM & Agent Engineering: Demonstrable experience designing, developing and deploying production-grade LLM applications and autonomous agent systems. This should include experience with multi-agent architectures, tool and function calling, agent memory, and agent orchestration. Exposure to frameworks such as LangChain, Google ADK or AutoGen, alongside an understanding of emerging standards such as MCP, is highly desirable.
• Strong Engineering & Machine Learning Foundation: Excellent software engineering and programming capabilities, underpinned by practical experience across machine learning. You should have deep expertise in at least one specialist area, such as deep learning, reinforcement learning, model fine-tuning or the development and optimisation of ML models.
• Excellent AI Model Selection & Architecture Skills: Ability to assess and work effectively across leading proprietary and open-source models, including those from OpenAI, Anthropic, Google and Meta. You should understand how to make informed architectural decisions around hosted versus self-hosted inference, RAG, fine-tuning, model selection and agent-based routing depending on the business and technical requirements.
• Strategic & Hands-On Technical Leadership: Able to operate at both architectural and implementation levels — shaping the overall AI strategy and solution design while remaining technically hands-on. Strong analytical reasoning, problem-solving and critical-thinking capabilities are essential, alongside the ability to apply mathematical concepts to complex technical challenges.
• LLM Evaluation, Monitoring & Continuous Improvement: Experience establishing robust evaluation methodologies for AI and LLM applications, together with production observability and tracing. Familiarity with platforms such as Langfuse or LangSmith is advantageous. You should be comfortable using real-world performance data and user feedback to continuously evaluate and improve AI systems.
• Business & Commercial Mindset: Strong interest in using AI to solve meaningful business problems rather than simply experimenting with technology. Able to translate technical capabilities into tangible business outcomes, efficiencies and measurable value.
• Cross-Functional Collaboration: Proven ability to work effectively alongside engineering, product, data and business stakeholders, balancing exploratory R&D with the reliability, scalability and standards expected of production systems.
• AI-Native Engineering Approach: Comfortable incorporating modern AI coding assistants such as Claude Code, Cursor and GitHub Copilot into the software development lifecycle. Demonstrates sound technical judgement when reviewing, validating, securing and governing AI-generated code.
• Continuous Innovation & Technical Curiosity: Naturally curious and proactive about emerging developments in AI. Regularly experiments with new technologies, research and techniques, translating relevant advancements into practical tools, products and solutions that can be scaled across internal or client environments.
• Experience taking AI initiatives from initial concept and experimentation through to production deployment and ongoing optimisation.
• Strong understanding of the end-to-end AI engineering lifecycle, with specialist depth in one or more stages.
• A portfolio or track record of production AI solutions incorporating autonomous or agentic functionality.
• Experience building enterprise AI solutions with security and governance embedded from the outset, including awareness of prompt injection risks, role-based access controls for agents, data protection and broader AI governance requirements.