PermanentIT & Software

Senior Software Engineer, Applied AI | On-site | George WC at Badger Holdings (Pty) Ltd

Location
George, Western Cape
Work model
On-site
Contract
Permanent
Minimum qualification
Bachelor's degree
Closing date
Not stated — check the original listing

First listed . Last checked at source .

In brief

**Overview** Badger Holdings (Pty) Ltd is a specialized insurance and related services company, founded in 1995, employing over 700 staff across South Africa and Australia, and insuring over 180,000 clients with premiums exceeding US$100 million. This role is within ARC AI, a division focused on building AI agents as products. These systems operate autonomously across business functions, handle real customer interactions, and deliver measurable outcomes within a regulated insurance environment. This is a production-focused function, not an experimentation role. **What you will do** You will design, build, and operate the AI agent systems that power ARC AI products, owning the full spectrum of activities including architecture, evaluation pipelines, production reliability, guardrails, and the backend integrations connecting agents to enterprise data. A key responsibility is to set the engineering standards for the team, emphasizing evaluation as a primary concern. This involves architecting enforcement mechanisms outside the model for security and ensuring compliance with POPIA and GDPR through initial architectural decisions. The architectural decisions made in this role will form the foundation for all subsequent engineering efforts. **Requirements (from the original advert)** **Non-negotiable:** * Demonstrated experience building and shipping AI agent systems in production (not demos or internal tools that never went live). * Ownership of an evaluation pipeline for a production AI system (defining metrics, building frameworks, and using them for deployment decisions). * Experience debugging production AI failures, tracing silent agent degradation to root causes in live systems. * Proficiency in Python and LLM frameworks (LangChain, LlamaIndex, or equivalent). * RAG architecture: retrieval pipeline design, vector database implementation, chunking and embedding strategy. * API design and backend integration at production scale. * Secure tool access patterns for agentic systems, understanding the boundary between LLM reasoning and deterministic enforcement. * Experience implementing guardrails: input validation, output filtering, and execution-layer prompt injection defense. * CI/CD for agentic systems, including implementing progressive delivery pipelines with instrumentation of tool invocations and decision points, staging with regression benchmarks, and canary deployment to detect behavioral drift. **Strong Advantage:** * Experience in regulated financial services, insurance, or healthcare environments. * Familiarity with graph-based agentic orchestration frameworks (LangGraph or equivalent), particularly durable execution and human-in-the-loop checkpointing in regulated environments. * Familiarity with Azure AI tooling and services. * MLOps practices: monitoring, observability, cost management for inference workloads. * CRM and enterprise system integration. **Educational Requirements:** * Bachelor's degree in Computer Science, Software Engineering, Information Technology, Artificial Intelligence, Data Science, or a related field. * OR equivalent practical industry experience building and deploying production-grade AI systems. **Who should apply** This role is ideal for a Senior Software Engineer who has a proven track record of building and operating AI agent systems in production environments. The candidate should understand the entire lifecycle of moving an AI agent from prototype to live deployment, with a strong emphasis on evaluation as a critical factor for delivering reliable AI products rather than just rapid iteration. Applicants should possess deep technical expertise in Python, LLM frameworks, RAG architecture, API design, and CI/CD for agentic systems, coupled with a commitment to architectural integrity, security, and regulatory compliance (POPIA, GDPR). Those with experience in regulated industries like financial services, insurance, or healthcare, and familiarity with advanced AI orchestration and MLOps practices, will have a strong advantage. **Deadline** Not specified **Reference** Original posting: https://www.myjobmag.co.za/job/senior-software-engineer-applied-ai-on-site-george-wc-badger-holdings-pty-ltd-3 Source: myjobmag

Summary drafted with AI assistance from the original advert. The advert itself is the authority — how we use AI.

At a glance

    • Python
    • Azure

    Extracted automatically from the advert; confirm requirements on the original listing.

    Job description

    - Badger Holdings is a specialised insurance and related services company. Founded in 1995, we currently employ over 700 staff members across South Africa and Australia and insure over 180 000 clients with premiums in excess of US$100 million. Through a unique blend of skills and expertise, Badger Holdings has grown into a formidable force in the insurance ... Senior Software Engineer, Applied AI | On-site | George WC ---------------------------------------------------------- * Job Type Full Time , Onsite * Qualification Bachelors * Experience * Location Western Cape * City George * Job Field Data, Business Analysis and AI  , ICT / Computer About the Role ARC AI builds AI agents as products: systems that operate autonomously across business functions, handle real customer interactions, and deliver measurable outcomes in a regulated insurance environment. This is not an experimentation function. We ship. We are looking for a Senior Software Engineer who has built and operated AI agent systems in production. Someone who knows what it takes to move an agent from prototype to live deployment, and who understands that evaluation, not iteration speed, separates reliable AI products from expensive demos. Requirements What You Will Own * You will design, build, and operate the AI agent systems that power ARC AI products. This means owning the full arc: architecture, evaluation pipelines, production reliability, guardrails, and the backend integrations that connect agents to real enterprise data. * You will set the engineering standards the rest of the team follows. Evaluation is a first-class responsibility here, not a QA afterthought. Securing an agent means architecting enforcement outside the model; defences sit at the execution boundary, not inside the system prompt. Compliance with POPIA and GDPR is an architectural decision you make at the start, not a checkpoint at the end. * The architectural decisions you make in this role will be the ones every subsequent engineer builds on. What We Require Non-negotiable * Demonstrated experience building and shipping AI agent systems in production: not demos, not internal tools that never went live * Ownership of an evaluation pipeline for a production AI system: you defined the metrics, built the framework, and used it to make deployment decisions * Experience debugging production AI failures: you have traced a silent agent degradation to its root cause in a live system * Proficiency in Python and LLM frameworks (LangChain, LlamaIndex, or equivalent) * RAG architecture: retrieval pipeline design, vector database implementation, chunking and embedding strategy * API design and backend integration at production scale * Secure tool access patterns for agentic systems: you know where LLM reasoning ends and deterministic enforcement must begin, and you have built the boundary between them * Experience implementing guardrails: input validation, output filtering, and execution-layer prompt injection defence * CI/CD for agentic systems: you have implemented progressive delivery pipelines for agents, including instrumentation of tool invocations and decision points, staging with regression benchmarks, and canary deployment to detect behavioural drift before full rollout Strong Advantage * Experience in regulated financial services, insurance, or healthcare environments * Familiarity with graph-based agentic orchestration frameworks (LangGraph or equivalent), particularly durable execution and human-in-the-loop checkpointing in regulated environments * Familiarity with Azure AI tooling and services * MLOps practices: monitoring, observability, cost management for inference workloads * CRM and enterprise system integration Educational Requirements * Bachelor's degree in Computer Science, Software Engineering, Information Technology, Artificial Intelligence, Data Science, or a related field * OR equivalent practical industry experience building and deploying production-grade AI systems Check how your CV matches this job Method of Application ------------------------- Interested and qualified? Go to Badger Holdings (Pty) Ltd on badgerholdings.mcidirecthire.com to apply Build your CV for free. Download in different templates.

    Before you apply

    • Confirm the requirements and closing date on the original listing (myjobmag). SPANi lists vacancies from other sites and may not reflect last-minute changes.
    • Legitimate employers do not charge application, registration or training fees.
    • Don't send your ID or bank details before you have confirmed the employer is real.

    How to spot a job scam

    Applying for permanent roles

    • Mirror the job title and top three requirements in your CV summary and most recent experience.
    • Quantify results where possible: sales targets, cases handled, tickets closed, or team size.
    • Proofread contact details and filenames before submitting — small errors cost interviews.
    • Verify the company and role on the source page before sharing ID copies or banking details.

    Similar roles

    Senior Software Engineer, Applied AI | On-site | George WC at Badger Holdings (Pty) Ltd | SPANi - South African Jobs