Production ML Engineer — Fast, Fair Product Discovery

Solenya; Cape Town; On-site; ZAR 900,000 - 1,400,000; Full time

Benefits offered by this job

free pickles

Job summary

Solenya in Cape Town seeks a Machine Learning Engineer to bring zero-shot discovery models from research to production, building scalable, reliable systems.

You will deploy models, optimize latency, and collaborate with researchers while advancing MLOps pipelines, CUDA tuning, and quantization strategies. This role is grounded in production-focused ML engineering with strong software practices.

Qualifications

• 3+ years of ML engineering experience.
• Proficient in PyTorch and deep learning fundamentals.
• Experience with ONNX, TensorRT, or model quantization.
• Strong software engineering skills (Python, testing, CI/CD).
• Familiarity with distributed training and serving infrastructure.

Responsibilities

• Deploy and optimize ML models for production serving.
• Build robust MLOps pipelines for training, evaluation, and deployment.
• Optimize CUDA kernels and model inference for latency-critical applications.
• Implement micro-batching, caching, and quantization strategies.
• Collaborate with researchers to productionize novel architectures.

Skills

Deep learning fundamentals

Software engineering practices

Distributed training

Tools

PyTorch

ONNX

TensorRT

Python

CI/CD

Job description

Solenya in Cape Town seeks a Machine Learning Engineer to bring zero-shot discovery models from research to production, building scalable, reliable systems.

You will deploy models, optimize latency, and collaborate with researchers while advancing MLOps pipelines, CUDA tuning, and quantization strategies. This role is grounded in production-focused ML engineering with strong software practices.