Overview
Unico Connect is seeking an MLOps Engineer to operate the infrastructure that takes ML and LLM models from notebooks to reliable production. The role spans CI/CD for models, observability for non-deterministic systems, deployment automation, and the platform tooling that lets AI Engineers ship faster. The position is well suited to engineers who enjoy the intersection of infrastructure, ML systems, and developer productivity.
Key Responsibilities
- Operate model deployment pipelines on GCP Vertex AI, AWS SageMaker, or self-hosted Kubernetes
- Maintain CI/CD for ML including data validation, model training, evaluation gates, and deployment
- Build observability for production models covering latency, cost, drift, and hallucination rate
- Implement A/B and canary rollouts for ML and LLM features
- Maintain model registries, feature stores, and experiment tracking with MLflow or Weights & Biases
- Partner with AI Engineers to harden development to staging to production flows
- Govern model versioning, prompt versioning, and rollback procedures
- Author runbooks for common ML production incidents including drift and cost spikes
- Maintain Terraform modules and Kubernetes manifests for shared ML platform components
- Participate in on-call rotations for ML platform incidents
Required Qualifications
- Bachelor's degree in Computer Science or a related field
- 1-3 years of experience in MLOps, DevOps, or backend engineering with ML exposure
- Strong Python; comfortable reading PyTorch or TensorFlow code
- Hands-on with Docker, Kubernetes, and at least 1 cloud (GCP or AWS)
- Familiarity with MLflow, Weights & Biases, or comparable experiment tracking
- Working knowledge of CI/CD with GitHub Actions or Cloud Build
- Comfort reading and modifying Terraform modules
- Basic understanding of model evaluation metrics and statistical significance
- Strong fundamentals in observability concepts including SLOs and alerting
- Excellent written communication for runbook and incident documentation
Preferred Qualifications
- LLM ops experience with LangSmith, Langfuse, or prompt versioning workflows
- Terraform or Pulumi for infrastructure as code
- Data engineering background including dbt and Airflow
- Hands-on with Ray, Triton, or vLLM serving
- Cost optimisation track record on cloud ML platforms
AI Tools Proficiency
Production engineering at Unico Connect assumes AI tools form part of the daily workflow rather than an experimental augmentation. For this role specifically:
- Cursor or Claude Code for Terraform and infrastructure work
- LangSmith for LLM ops and production observability
- AI-assisted Grafana, Datadog, or Honeycomb dashboards
- Claude or ChatGPT for runbook and post-mortem drafting
What we look for at Unico Connect
Every Unico role expects the same underlying traits — regardless of department or seniority. If these resonate, apply.
Fluent with Claude, ChatGPT, Cursor, Figma AI, or whatever is relevant to your craft. We expect AI tools in the loop, not as a novelty.
Fast cycles, real ownership, low ceremony. You will not be a cog.
Output and outcomes matter more than process. You ship work that moves a metric.
You treat the codebase, the deliverable, and the client relationship as your own.
You joined because you want to ship amazing tech products, not warm a seat.