AI Infrastructure Engineer [Tooling]
Tessera Labs3 hours ago
Remote, United StatesMid Level / Senior
Base Salary
$200k - $230k/yr
Responsibilities
- Build and maintain Python or Go CLIs, SDKs, and services for provisioning, deploying, testing, and debugging AI agents.
- Deploy, scale, and tune LLM inference with vLLM or comparable serving stacks, including GPU scheduling, autoscaling, batching, and cost and latency optimization.
- Build multi-agent infrastructure including agent runtimes, tool and connector execution, sandboxing, state management, and safe agent-version rollouts.
- Own MLOps workflows for model and prompt versioning, evaluation pipelines, artifact registries, and staging-to-production promotion.
- Write Kubernetes operators and custom controllers using CRDs to manage AI workloads.
- Design, build, and operate production AI infrastructure with Kubernetes and Terraform across Azure, Oracle Cloud, GCP, and AWS.
- Improve observability for agent and LLM calls, including tracing, token and GPU utilization, latency, errors, and cost.
- Design and own CI/CD, GitOps, release automation, environment provisioning, secret rotation, dependency updates, and compliance checks.
- Partner with AI, product, and platform engineers while mentoring others and contributing to platform technical direction at the senior level.
Requirements
- 5+ years of experience in infrastructure, platform, or backend engineering; 7+ years for senior level.
- Strong production software engineering experience in Python or Go, including tools, CLIs, or services used by other engineers.
- Hands-on experience running production LLM workloads with vLLM or comparable stacks such as TGI, Triton, SGLang, or Ray Serve.
- Experience building infrastructure for AI agents or LLM applications, including orchestration, tool calling, evaluation, or agent runtimes.
- Practical MLOps experience with model and prompt versioning, evaluation and release pipelines, and ML-system observability.
- Strong Kubernetes experience, including writing or extending operators and controllers with tools such as Kubebuilder, Operator SDK, controller-runtime, or Kopf.
- Strong Terraform experience and hands-on experience with at least one of Azure, Oracle Cloud, GCP, or AWS.
- Proven experience designing and owning CI/CD systems, GitOps deployments, release automation, and production systems.
- Solid networking fundamentals.
- Preferred experience includes GPU infrastructure, agent frameworks and protocols, LLM observability, GitOps controllers, cloud security, DevSecOps, service mesh, private connectivity, multi-cloud networking, and open-source contributions.
- Ability to make and defend infrastructure decisions, work independently, write production-quality code, and operate effectively in startup or big-tech environments.
Benefits
- Opportunity to work on cutting-edge AI infrastructure with enterprise impact.
- Ownership of foundational systems at an early-stage, high-growth company.
- Collaboration with an execution-focused founding team.
- Opportunity to shape how AI agents are deployed across major enterprise platforms.
Tech Stack
Categories
About Tessera Labs
Tessera Labs builds multi-agent AI systems that automate complex enterprise workflows across platforms such as SAP, Salesforce, Workday, Snowflake, and Databricks. It sells AI automation software and services to large organizations seeking to operationalize AI in back-office and data operations. Founded in 2022 and headquartered in London, the privately held company focuses on deploying production AI within existing enterprise stacks.