Lead AI LLM Engineer

e-Merge IT Recruitment; Sandton; On-site; ZAR 1,350,000 - 1,650,000; Full time

Job summary

e-Merge IT Recruitment is seeking a Lead AI Engineer to shape production AI systems in a cutting-edge environment. You will own end-to-end delivery across voice agents, LLM QA pipelines, and post-call intelligence, while mentoring engineers and driving scalable architectures on Azure.

The role requires hands-on leadership, strong Python skills, and experience deploying AI/ML solutions in production with a focus on reliability and cost efficiency in a modern cloud setup. Based in Sandton.

Qualifications

• 7+ years software engineering experience.
• 3+ years shipping LLM and/or speech+LLM systems to production.
• Strong production Python programming.
• Deep experience in at least two of: voice/conversational agents, speech pipelines, LLM evaluation, multi-agent/tool-calling systems.
• Solid Azure experience (serverless and/or Kubernetes, queues/messaging, blob storage, SQL, secrets/identity).
• Prompt engineering for multi-step, compliance-sensitive workflows.
• Proven player-coach leadership in a small agile team.

Responsibilities

• Own end-to-end delivery for one or more major areas (voice agents, speech/LLM QA pipelines, post-call intelligence, or text-channel agents).
• Partner with the head of AI on architecture, priorities, and production risk; turn decisions into shipped systems.
• Design and build production Python services on Azure (Functions and/or Kubernetes workers, messaging, storage, SQL-backed outcomes).
• Lead prompt/agent design, structured LLM outputs, evaluation/regression suites, and operational reliability.
• Drive post-call intelligence quality: scoring accuracy, structured output reliability, and pipeline performance.
• Mentor senior and junior engineers through design reviews, pairing, and code review.
• Collaborate with the platform portal team so campaigns, dashboards, and QA surfaces stay aligned with the AI runtime.
• Work with Azure DevOps on deployability, GPU/LLM cost trade-offs, and production operations.

Skills

Python

Leadership

Prompt engineering

LLM systems

Tools

Azure

Kubernetes

SQL

Blob storage

App Insights

Grafana

Job description

Ready to take the lead in building the next generation of AI-powered solutions?

This is an exciting opportunity for a Lead AI Engineer to join a dynamic technology environment where cutting-edge AI is being turned into real-world, production-ready solutions. You’ll work across LLMs, voice agents, speech technologies, automated testing, AI coding tools, and modern software development practices, while taking ownership of key technical initiatives and helping shape the future of conversational AI.

If you’re a hands-on technical leader who enjoys solving complex engineering challenges, mentoring others, and turning innovative ideas into scalable production systems, this could be the opportunity you’ve been looking for.

Must-have skills and experience:

• 7+ years software engineering, 3+ years shipping LLM and/or speech+LLM systems to production
• Strong production Python
• Deep experience in at least two of: voice/conversational agents, speech pipelines (STT/diarization/VAD), LLM evaluation, multi-agent/tool-calling systems
• Solid Azure experience (serverless and/or Kubernetes, queues/messaging, blob storage, SQL, secrets/identity)
• Prompt engineering for multi-step, compliance-sensitive workflows
• Proven player-coach leadership in a small agile team

Strong advantages:

• Experience with AI coding assistants such as Cursor, Claude, or similar
• Voice platform experience and STT/TTS vendor tuning
• Whisper / diarization / vLLM / OpenAI Batch / structured outputs
• Contact-centre, collections, or BPO domain experience
• Observability (Application Insights, Grafana) and CI/CD collaboration
• WhatsApp / email bot experience

Responsibilities:

• Own end-to-end delivery for one or more major areas (voice agents, speech/LLM QA pipelines, post-call intelligence, or text-channel agents)
• Partner with the head of AI on architecture, priorities, and production risk; turn decisions into shipped systems
• Design and build production Python services on Azure (Functions and/or Kubernetes workers, messaging, storage, SQL-backed outcomes)
• Lead prompt/agent design, structured LLM outputs, evaluation/regression suites, and operational reliability (latency, cost, failure handling, observability)
• Drive post-call intelligence quality: scoring accuracy, structured output reliability, and pipeline performance
• Mentor senior Junior engineers through design reviews, pairing, and code review
• Collaborate with the platform portal team so campaigns, dashboards, and QA surfaces stay aligned with the AI runtime
• Work with Azure DevOps on deployability, GPU/LLM cost trade-offs, and production operations

Reference number for this position is GZ61522 which is a permanent position based in Sandton offering a salary of R1.5m per annum, negotiable based on experience and ability.