Machine Learning Engineer

We’re building production-grade NLP systems and need someone who can take a model from research to reliable, scalable deployment. You’ll own the full lifecycle — from containerisation to live inference endpoints.

What you’ll do

• Package, serve, and monitor small language models on AWS SageMaker Serverless endpoints with optimised cold-start behaviour

• Build slim multi-stage Docker images, push to ECR, and keep inference images under tight size budgets

• Own the build → test → push → deploy CI/CD pipeline for ML services

• Configure IAM roles and manage secrets via AWS Secrets Manager following least-privilege principles

• Version datasets, models, and experiments; instrument latency, throughput, and accuracy in production

• Work with NLP libraries (spaCy, Transformers, FAISS, PyTorch) to build and iterate on NLP pipelines

Requirements:

Cloud & infrastructure:

• Docker — multi-stage builds, image optimisation

• AWS: ECR, IAM roles, Secrets Manager, SageMaker Serverless endpoint configuration

• CI/CD pipelines: build / test / push / deploy for ML services (GitHub Actions or similar)

ML & NLP:

• PyTorch, Hugging Face Transformers, spaCy, FAISS

• Hands-on experience running and tuning small language models (≤7B params) — spinning them up, stress-testing, optimising for latency and throughput

• Familiarity with quantisation (GGUF, ONNX, bitsandbytes) or model distillation

Nice to have

• RAG pipeline experience

Відгукнутись на вакансію