Senior AI Engineer

OfferZen Enterprise; Johannesburg; Hybrid; ZAR 1,200,000 - 2,000,000; Full time

Benefits offered by this job

Pension

Medical aid

Life cover

Study allowances

Job summary

OfferZen Enterprise is building production AI products for contact-centre and debt-collection operations in Johannesburg. The team ships real-time voice agents, automated QA scoring, and observability tools, with upcoming text-based agents for email and WhatsApp.

We work with Cursor and Claude and offer flexibility for remote work depending on role needs. The engineering team collaborates across frontend, backend, and cloud infra, using Azure Functions, Kubernetes, and modern AI tech to ship

Qualifications

• 5+ years engineering; 2+ years applied LLM / speech AI in production
• Strong Python (APIs, typing/validation, testing, packaging)
• OpenAI / Azure OpenAI (chat, structured outputs, batch patterns)
• Azure messaging, storage, and SQL-backed services
• Proven ownership of ambiguous, multi-system features

Responsibilities

• Build and harden real-time voice agents: modular prompts, multi-assistant flows, tool-calling, webhooks, telephony/operational concerns
• Improve automated QA pipelines: VAD, diarization, language gating, transcription, alignment/attribution, LLM scorecard scoring
• Implement structured LLM pipelines (schemas, batching, failure handling, score recalculation)
• Own features in Azure Functions / Kubernetes workers: queue consumers, artefact pipelines, SQL integrations
• Contribute to post-call intelligence features such as outcome scoring, summary generation, and structured data extraction
• Expand and maintain evaluation suites (scenarios, LLM-as-judge, CI regression)
• Contribute to email/WhatsApp agent work with reuse of tools, outcomes, and observability
• Review code; unblock Intermediate/Junior engineers; improve runbooks and operational quality
• Use AI coding tools (e.g. Cursor, Claude) as a normal part of day-to-day delivery

Skills

Python

LLM production

Speech AI

OpenAI/Azure

Azure services

Kubernetes

SQL databases

PyTorch

CI/CD

AI tooling

Tools

Cursor

Claude

Azure Functions

Kubernetes

Azure SQL

Job description

We build production AI products for contact-centre and debt-collection operations: real-time voice agents, automated call QA (speech + LLM scoring), and a client-facing platform portal that gives clients observability into AI performance and self-service control over their campaigns and configurations. Upcoming work includes text-based agents for email and WhatsApp.

Team:

Small, agile AI engineering team led by the Head of AI, with a Lead AI Engineer, Senior / Intermediate / Junior AI Engineers, Analyst, and Tester. We work closely with a Frontend Engineer, Lead Backend Engineer (platform portal), Azure DevOps/infra, and the wider IT department. We move quickly and use modern production AI and cloud technologies.

How We Work:

AI development tools such as Cursor and Claude are available and encouraged. Practical knowledge and experience using these (or similar AI coding assistants) is preferable.

Location & Employment:

Johannesburg, with flexibility for remote work depending on the candidate and role needs. All positions are permanent.

Pension, medical aid, life cover, and study allowances by arrangement.

What We’re Looking For:

High-autonomy engineer who designs and ships production AI features end-to-end across voice agents and/or automated call QA, including Azure integrations and evaluation.

Responsibilities

• Build and harden real-time voice agents: modular prompts, multi-assistant flows, tool-calling, webhooks, telephony/operational concerns
• Improve automated QA pipelines: VAD, diarization, language gating, transcription, alignment/attribution, LLM scorecard scoring
• Implement structured LLM pipelines (schemas, batching, failure handling, score recalculation)
• Own features in Azure Functions / Kubernetes workers: queue consumers, artefact pipelines, SQL integrations
• Contribute to post-call intelligence features such as outcome scoring, summary generation, and structured data extraction
• Expand and maintain evaluation suites (scenarios, LLM-as-judge, CI regression)
• Contribute to email/WhatsApp agent work with reuse of tools, outcomes, and observability
• Review code; unblock Intermediate/Junior engineers; improve runbooks and operational quality
• Use AI coding tools (e.g. Cursor, Claude) as a normal part of day-to-day delivery

Must-Have Skills & Experience

• 5+ years engineering; 2+ years applied LLM / speech AI in production
• Strong Python (APIs, typing/validation, testing, packaging)
• OpenAI / Azure OpenAI (chat, structured outputs, batch patterns)
• Azure messaging, storage, and SQL-backed services
• Proven ownership of ambiguous, multi-system features

Preferable / Strong Advantages

• Experience with Cursor, Claude, or similar AI coding assistants
• Voice agent stacks; latency, barge-in, endpointing awareness
• Speech ML in production (PyTorch, Whisper, diarization, ONNX, GPU Docker)
• vLLM / guided decoding; Kubernetes worker patterns
• SQLAlchemy / Azure SQL; IaC awareness or strong infra collaboration