MLOps Engineer (Relocation to Serbia)
This engagement is focused on building an internal AI platform that enables developers to ship AI-powered services efficiently. Scope includes model connectivity, prompt testing and evaluation, monitoring/observability, and the underlying AI infrastructure layer.
The objective is to improve DevEx and reduce time-to-market for AI features.
Tasks
Build and operate the AI platform infrastructure enabling developers to ship LLM-based services faster.
Implement and maintain Kubernetes-based runtime environments (incl. AKS) for AI workloads.
Manage infrastructure as code with Terraform (modules, environments, CI/CD automation).
Support LLM workflows: RAG, agents, prompt experimentation, evaluations, and deployment patterns.
Integrate and operate tooling such as Azure AI Foundry, LiteLLM, Langfuse, MLflow.
Orchestrate pipelines using Kubeflow Pipelines and/or Argo Workflows (build, deploy, evaluate).
Improve platform reliability and observability (monitoring, logging, tracing, cost/perf signals).
Collaborate closely with developers to streamline DX (APIs, templates, docs, golden paths, automation).
Requirements
Strong hands-on experience with Kubernetes in production (preferably AKS).
Solid Terraform expertise (IaC best practices, multi-env setups).
Practical experience supporting ML/LLM workloads in a platform or DevOps/MLOps context.
Proficiency in Python for automation, scripting, and supporting APIs/evaluation tooling.
Understanding of CI/CD, release processes, and production-grade operations.
Ability to work under tight timelines and deliver pragmatically.
Nice to Have
Experience building internal developer platforms or “paved roads” for engineering teams.
Familiarity with LLM evaluation frameworks, prompt testing workflows, and LLM observability.
Exposure to RAG architectures, vector databases, and agentic patterns.
Experience with Kubeflow, Argo, and ML lifecycle tooling.
Engagement Type
Long-term B2B contract.
Team
You will join a team of 5, with 3 AI Platform Engineers being added.
Location / Timezone
Remote within Europe (preferred: Croatia, Poland, Portugal, Serbia).
European working hours.
Occasionally available for meetings up to 10:00 AM PST (US overlap).
The objective is to improve DevEx and reduce time-to-market for AI features.
Tasks
Build and operate the AI platform infrastructure enabling developers to ship LLM-based services faster.
Implement and maintain Kubernetes-based runtime environments (incl. AKS) for AI workloads.
Manage infrastructure as code with Terraform (modules, environments, CI/CD automation).
Support LLM workflows: RAG, agents, prompt experimentation, evaluations, and deployment patterns.
Integrate and operate tooling such as Azure AI Foundry, LiteLLM, Langfuse, MLflow.
Orchestrate pipelines using Kubeflow Pipelines and/or Argo Workflows (build, deploy, evaluate).
Improve platform reliability and observability (monitoring, logging, tracing, cost/perf signals).
Collaborate closely with developers to streamline DX (APIs, templates, docs, golden paths, automation).
Requirements
Strong hands-on experience with Kubernetes in production (preferably AKS).
Solid Terraform expertise (IaC best practices, multi-env setups).
Practical experience supporting ML/LLM workloads in a platform or DevOps/MLOps context.
Proficiency in Python for automation, scripting, and supporting APIs/evaluation tooling.
Understanding of CI/CD, release processes, and production-grade operations.
Ability to work under tight timelines and deliver pragmatically.
Nice to Have
Experience building internal developer platforms or “paved roads” for engineering teams.
Familiarity with LLM evaluation frameworks, prompt testing workflows, and LLM observability.
Exposure to RAG architectures, vector databases, and agentic patterns.
Experience with Kubeflow, Argo, and ML lifecycle tooling.
Engagement Type
Long-term B2B contract.
Team
You will join a team of 5, with 3 AI Platform Engineers being added.
Location / Timezone
Remote within Europe (preferred: Croatia, Poland, Portugal, Serbia).
European working hours.
Occasionally available for meetings up to 10:00 AM PST (US overlap).