AI Engineer

Role summary Build and run the AI platform: the backend that gives products governed access to AI models and tools, the infrastructure it runs on, and the AI features built on top of it. Responsibilities Build and maintain backend services and APIs (REST, streaming) in Python or Go Deploy and operate services and AI model servers on Kubernetes, with Helm and CI/CD pipelines Implement authentication, access control and security controls: OAuth 2.0 / OIDC, API keys, secrets management, sensitive-data masking, audit logging Select, deploy and operate AI models, commercial and open-weight: LLMs, embedding models and speech models Build retrieval-augmented generation and agent features: vector and hybrid search, tool calling, multi-step workflows, guardrails Help teams integrate with the platform's APIs, and build tool services such as MCP servers Set up monitoring, dashboards and alerts; investigate and resolve incidents Write technical documentation, code samples and runbooks Technical requirements Degree in computer science, engineering or a related field, or equivalent experience Python; Go is a plus REST APIs, HTTP and JSON Linux, Git and Docker Hands-on experience with at least one LLM API (OpenAI, Anthropic, Google) Nice to have: More experience is a plus: professional years in backend, platform or ML engineering, and AI features shipped to production Kubernetes, Helm, Argo CD and CI/CD (GitHub Actions or GitLab CI) Model serving with vLLM or Ollama PostgreSQL, including pgvector, and Redis OAuth 2.0 / OIDC and a secrets manager such as HashiCorp Vault LLM or API gateways (LiteLLM, Envoy, Kong) and agent frameworks (MCP, A2A, LangGraph) Monitoring with Prometheus, Grafana, OpenTelemetry or Langfuse Experience mentoring other engineers Work with regulated or sensitive data Technical requirements Degree in computer science, engineering or a related field, or equivalent experience Python; Go is a plus REST APIs, HTTP and JSON Linux, Git and Docker Hands-on experience with at least one LLM API (OpenAI, Anthropic, Google) Nice to have: More experience is a plus: professional years in backend, platform or ML engineering, and AI features shipped to production Kubernetes, Helm, Argo CD and CI/CD (GitHub Actions or GitLab CI) Model serving with vLLM or Ollama PostgreSQL, including pgvector, and Redis OAuth 2.0 / OIDC and a secrets manager such as HashiCorp Vault LLM or API gateways (LiteLLM, Envoy, Kong) and agent frameworks (MCP, A2A, LangGraph) Monitoring with Prometheus, Grafana, OpenTelemetry or Langfuse Experience mentoring other engineers Work with regulated or sensitive data