Senior Full Stack Engineer - AI

the-global-talent-co; South Africa; On-site; ZAR 900,000 - 1,300,000; Full time

Job summary

The Global Talent Co is seeking a highly autonomous Senior Full Stack Engineer with strong experience building and shipping production software across the stack, combined with hands-on experience developing and operating AI/LLM-powered applications in production. You will be one of the first engineering hires, owning technical decisions, standards, architecture, and the product itself.

You will own problems from the initial conversation with the grant team through to production, driving usable

Qualifications

• Proficient in TypeScript and Node.js with several years of professional experience.
• Deep Postgres knowledge, including JSONB, performance, and migrations.
• Full-stack skills across Next.js/React Query, Express, BullMQ, and AWS ECS/RDS.
• Experience building and operating AI pipelines in production with LLMs.
• Strong prompt engineering, context management, model selection, and AI evaluation.
• High autonomy, ownership, usability-focused, and proactive problem-solving.

Responsibilities

• Build and ship end-to-end product features independently, including the user interface.
• Work confidently across the frontend, backend, infrastructure, and AI pipeline.
• Build from real user problems by working closely with the grant team, rather than predefined tickets.
• Develop interfaces with a usability-first mindset, ensuring the product genuinely works for grant writers.
• Take ownership of problems from initial discovery through to production deployment.
• Contribute to reducing the time from starting a new project to a finished, submitted application through product improvements, automation, and better workflows.

Skills

TypeScript

Node.js

Postgres

JSONB

Next.js

React Query

Express

BullMQ

AWS

Terraform

AI pipelines

LLMs

Prompt engineering

Debugging

Autonomy

Usability

Claude Code

Cursor

Tools

Claude Code

Cursor

Job description

SENIOR FULL STACK ENGINEER - AI

The Role

You will join the company , which is building the digital infrastructure for grant funding , helping organizations spend less time navigating funding logic, forms, and administration and more time on the projects and impact that matter.

The platform brings together research across 18,000+ funding programmes, AI-supported analysis and application drafting, expert review, and ongoing grant management . AI handles what can scale, while people bring experience and judgement where it matters.

As a Senior Full Stack Engineer , you will work end-to-end on AntragPlus , contributing across the backend, frontend, infrastructure, and AI pipeline at the core of the platform.

You will be one of the company's first engineering hires , with significant ownership over technical decisions, engineering standards, architecture, and the product itself. You will own problems from the initial conversation with the grant team through to production, rather than simply working from predefined tickets.

Position: Senior Full Stack Engineer - AI

Seeking a highly autonomous Senior Full Stack Engineer with strong experience building and shipping production software across the stack, combined with hands‑on experience developing and operating AI/LLM-powered applications in production .

The ideal candidate combines strong technical depth with a high-ownership mindset , a usability-first approach, and the ability to identify and solve problems independently in an environment where not everything is fully defined yet.

Responsibilities

Product Development & Full-Stack Engineering

• Build and ship end-to-end product features independently, including the user interface.
• Work confidently across the frontend, backend, infrastructure, and AI pipeline.
• Build from real user problems by working closely with the grant team , rather than simply implementing predefined tickets.
• Develop interfaces with a usability-first mindset , ensuring the product genuinely works for grant writers.
• Take ownership of problems from initial discovery through to production deployment.
• Contribute to reducing the time from starting a new project to a finished, submitted application through product improvements, automation, and better workflows.

AI Development & Evaluation

• Advance the platform's AI capabilities through prompt engineering, context management, cost control, and multi‑provider AI setups.
• Work with AI providers including AWS Bedrock, Anthropic, and OpenAI.
• Build and operate AI pipelines in production , going beyond simply calling an API.
• Develop and own the company's AI evaluation practice , including prompt quality, model selection, and regression detection.
• Work with AI agents and tool‑calling workflows where applicable.
• Use AI-native development tools such as Claude Code or Cursor as part of your engineering workflow.

Production, Infrastructure & Reliability

• Operate, monitor, and debug the live production environment.
• Work with tools including Sentry, CloudWatch, and Postgres performance monitoring.
• Contribute to infrastructure running on AWS , including ECS and RDS.
• Maintain and improve production reliability and performance.
• Identify and resolve technical issues with a strong debugging instinct in live systems.

Engineering Architecture & Technical Leadership

• Shape the company's technical architecture, code quality, engineering standards, and technical roadmap.
• Help establish how the engineering team works and the technical standards it follows.
• Identify better technical solutions proactively rather than waiting for predefined tasks.
• Take complete ownership of technical problems and drive them through to resolution.
• Contribute to building scalable technical foundations as one of the company's first engineering hires.

Requirements

Several years of professional experience with TypeScript and Node.js.

Strong depth in Postgres , including JSONB, query performance, and migrations.

Strong full‑stack capabilities, with experience across:

• Next.js 15 / React Query
• Express / BullMQ
• AWS (ECS, RDS)
• Terraform

Hands‑on experience building and operating AI pipelines in production , beyond simply integrating an AI API.

Experience working with LLMs and AI‑powered applications.

Strong understanding of prompt engineering, context management, model selection, and AI evaluation.

Strong debugging skills in live production systems.

High level of autonomy and ownership , with the ability to identify problems, develop solutions, and close the loop without hand‑holding.

Usability‑first mindset , with the ability to build interfaces that genuinely work for end users.

Comfortable working in an environment where not everything is fully defined and where engineers are expected to proactively shape solutions.

AI‑native approach to software development , with familiarity using tools such as Claude Code or Cursor.