Machine Learning Engineer

Solenya

Cape Town

On-site

ZAR 900,000 - 1,300,000

Full time

14 days+

Get a reply from this employer

Your resume and cover letter, tailored to exactly what they’re hiring for.

Get past ATS filters

Job summary

Solenya is building the AI infrastructure layer for modern e-commerce from Cape Town. We search for an ML engineer to join a small, generalist-focused team handling model serving, data pipelines, and API infrastructure that underpins millions of requests daily.

You’ll deploy models from research to production, optimize inference, and contribute across backend, infra and ML tasks. This is a hands-on role with strong collaboration with leadership and a foundation in Python.

Qualifications

  • 3+ years of experience in ML engineering or related roles.
  • Strong Python and software engineering fundamentals.
  • Experience deploying ML models in production.
  • Knowledge of PyTorch and deep learning concepts.
  • Ability to work across ML, backend and infra tasks.

Responsibilities

  • Take new models from research to production, with fast GPU inference.
  • Build and maintain the pipelines that ingest and embed merchant catalogues.
  • Develop features in our GraphQL API used by merchants and developers.
  • Manage Kubernetes infrastructure on GCP, including deployments and observability.
  • Keep training and evaluation pipelines reproducible.
  • Self-host and run LLMs for judging, annotation and evaluation.

Skills

Python
CI/CD & testing
ML deployment in production
PyTorch
Cloud infrastructure
Backend services

Tools

PyTorch
GraphQL
Kubernetes
GKE
FastAPI

Job description

Experience: 3+ years of experience in ML engineering or related roles.

About Solenya

Solenya is building the AI infrastructure layer for modern e-commerce. We help merchants better match products to customers so shoppers can discover the right products faster. This drives higher revenue, stronger engagement and better customer lifetime value.

We’re an early-stage team working closely with leading retailers and marketplaces to shape the future of AI-driven commerce.

The Role

We're looking for another ML engineer to join our small team of generalists. Between them, they look after everything that makes the product work: model serving, data pipelines, the API merchants integrate with, and the infrastructure underneath it all. Together, that handles millions of requests a day.

The focus changes from week to week. One week you might be deploying a new model from our researchers or speeding up inference, the next adding an API feature for a customer or fixing a pipeline. You'll work closely with the leadership team and own the parts of the system you build.

What You’ll Do
  • Help take new models from research to production, and keep GPU inference fast and cost-effective
  • Build and maintain the pipelines that ingest and embed merchant catalogues
  • Build features in our GraphQL API, which merchants and developers integrate with
  • Look after our Kubernetes infrastructure on GCP, including deployments and observability
  • Keep training and evaluation pipelines reproducible
  • Self-host and run LLMs for judging, annotation and evaluation
What We’re Looking For
  • Strong Python and software engineering fundamentals: testing, CI/CD and code others can maintain
  • Experience deploying and running ML models in production
  • Solid PyTorch and deep learning knowledge, enough to work alongside researchers
  • Comfortable with backend services, databases and cloud infrastructure
  • A generalist who’s happy switching between ML, backend and infra work
  • High EQ, low ego, and happy in an early-stage environment

Nice to have: Ray, Kubernetes, GPU performance work, vector databases, GraphQL, Kafka or LLM serving.

Our Stack
  • Backend: FastAPI, GraphQL (Strawberry), Prefect, Kafka
  • Infra: GKE with GPUs, Helm, Skaffold, Terraform, Nix, uv
What Success Looks Like

In your first 3–6 months, you'll:

  • Ship changes across the stack, from model serving and pipelines to the API and infrastructure
  • Measurably improve inference latency, cost or reliabilityOwn at least one part of the system that the rest of the team relies on
Why Join Solenya
  • Work at real scale from day one
  • Work closely with the leadership team
  • Broad exposure across ML, backend and infrastructure
Get your free, confidential resume review.

or drag and drop your file here.

Similar jobs

Similar jobs worth comparing

Machine Learning Researcher
Machine Learning Researcher

Solenya • Cape Town

On-site
ZAR 900,000 - 1,300,000
ML Engineer: Production-Grade AI for Scalable Commerce
ML Engineer: Production-Grade AI for Scalable Commerce

Solenya • Cape Town

On-site
ZAR 900,000 - 1,300,000
Senior ML Researcher: Multimodal Search & Recommendations
Senior ML Researcher: Multimodal Search & Recommendations

Solenya • Cape Town

On-site
ZAR 900,000 - 1,300,000
Senior ML Engineer
Senior ML Engineer

Boardroom Appointments • Cape Town

On-site
ZAR 900,000 - 1,500,000
MLOps/DevOps Engineer
MLOps/DevOps Engineer

Melio Consulting Pty • South Africa

On-site
ZAR 600,000 - 1,000,000
AI Engineer
AI Engineer

Vaimo • Pretoria

On-site
ZAR 600,000 - 800,000
Real-Time ML Engineer — AWS SageMaker & MLOps
Real-Time ML Engineer — AWS SageMaker & MLOps

Boardroom Appointments • Cape Town

On-site
ZAR 900,000 - 1,500,000
Senior Machine Learning Engineer
Senior Machine Learning Engineer

Myn • South Africa

Remote
ZAR 2,032,000 - 3,048,000
Machine Learning Engineer
Machine Learning Engineer

Global One • Cape Town

On-site
ZAR 500,000 - 700,000
Lead AI/ML Operations (MLOps) Engineer
Lead AI/ML Operations (MLOps) Engineer

Placements24 • East London

Hybrid
ZAR 1,000,000 - 1,800,000
Competitive salary
Bonus potential
Medical, dental, retirement plans
+2