ML Ops Engineer

About the Role

We are seeking a skilled MLOps Engineer to own how our AI and ML systems are built,

deployed and kept healthy in production. This role is ideal for someone who enjoys taking

models and LLM-powered features from experimentation to reliable, scalable services used

by clients every day.

The successful candidate will sit at the intersection of machine learning and infrastructure,

setting up the pipelines, cloud environments and monitoring that let our AI products and

client solutions ship quickly and run safely.

Key Responsibilities

ML & LLM Operations

• Build and maintain CI/CD pipelines for ML models and LLM-based features. • Set up

model and prompt versioning, experiment tracking and a model registry. • Run LLM

operations: API usage and cost control, evaluation pipelines and guardrails. • Build and

manage RAG infrastructure, including vector databases and document processing

pipelines (OCR, extraction).

Infrastructure & Deployment

• Deploy and scale model and inference services on AWS, GCP or Azure using

Docker and Kubernetes.

• Write infrastructure as code and clear runbooks so deployments are repeatable.

• Keep systems secure and compliant: secrets management, access control and client data isolation.

Monitoring & Reliability

• Monitor models in production for latency, cost, accuracy, data drift and failures, with

alerting. • Troubleshoot production issues and drive root-cause fixes.

Cross-Functional Collaboration

• Work with the AI Development Lead, developers and project managers to make releases

faster and safer.

• Participate in code reviews, sprint planning and Agile ceremonies.

Must-Have Skills

• Strong Python, plus solid Linux and shell scripting.

• Hands-on experience with Docker, Kubernetes and at least one major cloud

(AWS/GCP/Azure). • Experience with MLOps tools such as MLflow, Weights & Biases,

Kubeflow or Airflow. • Experience serving models or LLM APIs (FastAPI, vLLM, BentoML,

SageMaker, Vertex AI or similar).

• Working knowledge of vector databases (pgvector, Pinecone, Qdrant) and RAG

pipelines. • CI/CD (GitHub Actions, GitLab CI) and monitoring tools (Prometheus,

Grafana, ELK).

Nice-to-Have

• Experience with LLM observability tools (Langfuse, LangSmith, Arize).

• Fine-tuning experience (LoRA, PEFT).

• Infrastructure as Code with Terraform.

• Cost optimisation of GPU or LLM API workloads.

• Experience in a consulting or multi-client environment.

Qualifications

• Bachelor's degree in Computer Science, Engineering, or a related field (or equivalent

practical experience).

• 4+ years in DevOps, MLOps or ML engineering, with at least 2 years running ML or LLM

systems in production.

• Proven track record of production ML/AI deployments.

What We Offer

• Opportunity to work on cutting-edge AI-first, mobile-web integrated

platforms. • Dynamic, collaborative culture that values innovation and rapid

execution. • Competitive compensation with performance-based growth.

• Flexible remote-friendly work environment with hybrid collaboration where required.

To apply, please share:

• Updated CV

• GitHub/Portfolio

• Links to production systems or projects you have deployed

Email: [email protected]