Senior AI LLM Engineer - Sandton - R1.2m PA

E-Merge

Sandton

On-site

ZAR 1,000,000 - 1,400,000

Full time

4 days ago
Be an early applicant
Application generator

An application made for this job — a tailored resume and cover letter that speak straight to the posting.

Get past ATS filters

Job summary

E-Merge in Sandton is seeking an experienced AI engineer to build real-time voice agents and scalable AI solutions. You will work across LLMs, voice stacks, automated testing, and modern software practices to turn ambitious AI concepts into production-ready systems.

This permanent role offers a competitive salary of about R1.2 million per year, negotiable by experience, and the opportunity to own cross-system features end-to-end in a cutting-edge AI environment, with strong focus on delivery and

Qualifications

  • 5+ years engineering experience with 2+ years in production LLM / speech AI.
  • Strong Python (APIs, typing, testing, packaging).
  • Experience with OpenAI / Azure OpenAI in production.
  • Azure storage, messaging, 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, artifact 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

Skills

Python
LLM / speech AI
OpenAI / Azure OpenAI
Azure SQL
Multi-system ownership
Production systems

Tools

Azure Functions
Kubernetes
SQLAlchemy

Job description

Build what's next in AI.

Join an innovative technology environment focused on developing intelligent, AI-powered conversational solutions that are shaping the future of how people interact with technology.

This is a hands-on opportunity to work across LLMs, voice agents, automated testing, AI coding tools, and modern software development practices. You'll take on complex technical challenges, contribute to solution design, and help turn ambitious AI concepts into scalable, production-ready solutions.

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
Strong Advantages:
  • Experience with Cursor, Claude, or similar AI coding assistants
  • Voice agent stacks; latency, barge-in, end pointing awareness
  • Speech ML in production (PyTorch, Whisper, diarization, ONNX, GPU Docker)
  • vLLM / guided decoding; Kubernetes worker patterns
  • Contact-centre QA or collections domain
  • SQLAlchemy / Azure SQL; IaC awareness or strong infra collaboration
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, artifact 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

Reference Number for this position is GZ61523 which is a Permanent position based in Sandton offering a salary of R1.2m per annum, negotiable based on experience and ability.

Get your free, confidential resume review.
or drag and drop your file here.
Similar jobs

Similar jobs worth comparing

Lead AI LLM Engineer - Sandton - R1.5m PA
Lead AI LLM Engineer - Sandton - R1.5m PA

E-Merge • Sandton

On-site
ZAR 1,350,000 - 1,650,000
Intermediate AI LLM Engineer - Sandton - R800k PA
Intermediate AI LLM Engineer - Sandton - R800k PA

E-Merge • Sandton

On-site
ZAR 680,000 - 920,000
Lead AI LLM Engineer – Sandton – R1.5m PA
Lead AI LLM Engineer – Sandton – R1.5m PA

e-Merge IT Recruitment • Sandton

On-site
ZAR 1,350,000 - 1,650,000
Lead AI Engineer - Sandton, Johannesburg - up to R1.4mil per annum
Lead AI Engineer - Sandton, Johannesburg - up to R1.4mil per annum

E-Merge • South Africa

Hybrid
ZAR 1,260,000 - 1,540,000
Lead AI Engineer - Sandton - R1.4m PA
Lead AI Engineer - Sandton - R1.4m PA

E-Merge • Sandton

On-site
ZAR 1,260,000 - 1,540,000
Intermediate AI Engineer - Sandton, Johannesburg - up to R700k
Intermediate AI Engineer - Sandton, Johannesburg - up to R700k

E-Merge • South Africa

Hybrid
ZAR 480,000 - 700,000
Senior AI LLM Engineer — Real-Time Voice Systems
Senior AI LLM Engineer — Real-Time Voice Systems

E-Merge • Sandton

On-site
ZAR 1,000,000 - 1,400,000
Intermediate AI Engineer
Intermediate AI Engineer

E-Merge IT Recruitment • Sandton

Hybrid
ZAR 420,000 - 700,000
Hybrid work arrangement
Salary up to R700k per annum
Lead AI LLM Engineer: Production-Grade Conversational AI
Lead AI LLM Engineer: Production-Grade Conversational AI

e-Merge IT Recruitment • Sandton

On-site
ZAR 1,350,000 - 1,650,000
Lead AI LLM Engineer: Build Production-Conversational AI
Lead AI LLM Engineer: Build Production-Conversational AI

E-Merge • Sandton

On-site
ZAR 1,350,000 - 1,650,000