AI Infrastructure Engineer [Tooling]

New

Tessera LabsAI infrastructure

Remote in the U.S.Full-TimeMiddle

Salary$200K - $230K; $200K – $230K • Offers Equity

Apply NowOpens the employer's application page

Job Details

Experience: 5+ years of experience in infrastructure, platform, or backend engineering (7+ years for senior)
Required Skills: PythonKubernetesGoCI/CDTerraformMLOps

Have 5+ years of experience in infrastructure, platform, or backend engineering; senior-level candidates need 7+ years.
Demonstrate strong software engineering in Python or Go and experience shipping tools, CLIs, or services used by other engineers.
Have hands-on experience running production LLM workloads using vLLM or a comparable serving stack.
Have experience building infrastructure for AI agents or LLM applications, such as orchestration, tool calling, evaluation, or agent runtimes.
Have practical MLOps experience with model or prompt versioning, evaluation and release pipelines, and ML systems observability.
Have strong hands-on Kubernetes experience, including writing or extending operators or controllers.
Have strong hands-on Terraform experience and experience with at least one of Azure, Oracle Cloud, GCP, or AWS.
Have experience designing and owning CI/CD systems, GitOps-driven deployments, and release automation.
Have solid networking fundamentals.
Have experience deploying and operating production systems.

Build and maintain internal CLIs, SDKs, and services in Python or Go for provisioning, deploying, testing, and debugging AI agents.
Deploy, scale, and tune LLM inference using vLLM or similar serving stacks, including GPU scheduling, autoscaling, and batching.
Build infrastructure for multi-agent systems, including runtimes, tool and connector execution, sandboxing, and state management.
Own MLOps workflows for model and prompt versioning, evaluation, artifact registries, and release promotion.
Write Kubernetes operators and custom controllers for AI workload deployment and management.
Design, build, and operate AI agent infrastructure on Kubernetes and Terraform across cloud environments.
Improve observability for AI systems, including tracing, utilization, latency, errors, and cost.
Design and own CI/CD, GitOps, and release automation for infrastructure, services, and model or agent releases.
Build self-service tooling for environment provisioning, secret rotation, dependency updates, compliance checks, and release management.

View Full Description & ApplyYou'll be redirected to the employer's site