Senior Full Stack Engineer - AI

This position is listed on behalf of a partner company, who manages all applications and next steps. Our partner is looking for a Senior Full Stack Engineer – AI based in South Africa. This is a high-ownership engineering opportunity for a senior developer building AI-powered software from the ground up. You’ll work end-to-end across frontend, backend, infrastructure, and production AI pipelines. The role combines hands-on product development with technical architecture, reliability, and engineering leadership. You’ll work directly from real user problems, taking ideas from discovery through implementation, deployment, and iteration. Your work will help automate complex workflows and make it significantly easier for organizations to navigate and manage grant applications. As one of the early engineering hires, you’ll have substantial influence over architecture, technical standards, product direction, and engineering practices. This is an ideal environment for an autonomous engineer who enjoys ambiguity, moves quickly, and takes complete ownership of outcomes. Accountabilities Build and ship end-to-end product features independently, including user-facing interfaces, backend services, infrastructure, and AI-powered functionality.Work across the full technology stack to translate real user needs into practical, scalable product solutions.Collaborate directly with domain experts and users to identify problems, validate solutions, and improve workflows rather than simply implementing predefined tickets.Develop intuitive interfaces with a strong usability-first mindset, ensuring solutions genuinely meet end-user needs.Own technical problems from initial discovery through development, deployment, monitoring, and production resolution.Improve product workflows, automation, and functionality to reduce the time required to create and submit completed grant applications.Advance AI capabilities through prompt engineering, context management, model selection, cost optimization, and multi-provider AI architectures.Build and operate production AI pipelines using providers such as AWS Bedrock, Anthropic, and OpenAI.Develop AI evaluation practices covering prompt quality, model performance, regression detection, and ongoing optimization.Work with AI agents and tool-calling workflows where appropriate and incorporate AI-native development tools into daily engineering practices.Monitor, debug, and improve live production environments using tools such as Sentry, CloudWatch, and PostgreSQL performance monitoring.Contribute to AWS infrastructure, including ECS and RDS, while maintaining strong standards for reliability, scalability, and performance.Shape technical architecture, code quality, engineering standards, and the broader technical roadmap.Proactively identify better technical approaches and establish scalable engineering foundations as an early member of the engineering team. Requirements Several years of professional software engineering experience with strong expertise in TypeScript and Node.js.Strong PostgreSQL expertise, including experience with JSONB, query performance optimization, and database migrations.Demonstrated full-stack development experience across technologies such as Next.js 15, React Query, Express, and BullMQ.Practical experience with AWS services including ECS and RDS, as well as infrastructure-as-code using Terraform.Hands-on experience building, deploying, monitoring, and operating AI/LLM-powered applications and pipelines in production—not simply integrating an AI API.Strong understanding of prompt engineering, context management, model selection, cost considerations, and AI evaluation methodologies.Experience working with multiple AI providers and understanding how to design flexible, production-ready AI architectures.Strong debugging instincts and the ability to investigate and resolve issues in live production systems.Exceptional autonomy and ownership, with the ability to identify problems, develop solutions,