Senior Software Engineer, Applied AI
First seen by Alion on Oct 20, 2026.
Build AI systems that do more than demo well.
Our client builds AI agents that operate in the real world, handling customer interactions,
supporting business operations, and delivering measurable outcomes in a regulated
insurance environment. These are production systems used by real people, not proof-of-
concepts sitting in a sandbox.
We’re looking for a Senior Software Engineer who knows how to take AI agents from idea to
deployment and keep them reliable, secure, and scalable once they’re live.
If you thrive in high-ownership environments, enjoy solving complex engineering problems,
and care deeply about building AI systems responsibly, this role is for you.
Duties & Responsibilities
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.
Desired Experience & QualificationNon-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
We recognise that exceptional experience and demonstrated capability can be just as valuable as formal qualifications
Why Join?
- Build AI products that are actively used in the real world
- Work in a highly autonomous, engineering-led environment
- Influence architectural decisions from the ground up
- Join a small, senior team with meaningful ownership
- Work on technically challenging problems at the intersection of AI, reliability, and compliance
The Environment
You’ll be part of a small, high-impact team building something from the ground up. There are no layers of separation, no handoffs to QA, DevOps, or external teams. You own what you build.
Your work will directly shape how AI is experienced by real customers in a regulated environment. It’s complex, meaningful, and visible.
They're based in George, Western Cape, and this role is office-based, giving you the opportunity to collaborate closely, move quickly, and build as a team.
If you’ve built AI products that made it into users’ hands and you’re ready to take full ownership of what comes next, we’d like to hear from you.
Package & Remuneration
- Medical Aid and Retirement Annuity contribution
- Yearly bonus, payable in December - candidates starting now will only receive December 2027
- Yearly salary reviews
- 15 days annual leave | 3 days family leave | 2 days compassionate leave
- Longer service rewards and awards
- 3 year loyalty bonus, equivalent to 1 month salary | 3 year anniversary – every 3 years
- Learning & Development Opportunities
- There is a Sanlam Group Policy that comes into effect after 3 years of employment (paid by the company) – covers death, disability, and critical/serve illness