AI Platform Engineer
RemoteUnited States
Job Summary
Own the configuration, tooling, and infrastructure for a private, domain-aware AI assistant supporting engineers across Linux kernel drivers, firmware, ASIC development, and hardware/software integration. Design, implement, and improve a workforce of autonomous agents that automate operations via FastAPI REST APIs, CLI interfaces, and chat integration, routing work across a tiered model fleet. Maintain containerized services on Linux, reverse proxies, systemd timers, PostgreSQL, and Redis while hardening the platform and managing deployments. Author structured workflows and system instructions to ground model output in documentation and code, then build CI/CD validation pipelines to catch configuration errors and broken agent contracts. Track platform costs, model selection, and token usage to optimize value, while evaluating new tools and upgrades to keep the engineering environment current.
Required Qualifications
- B.S. or M.S. in Computer Science, Engineering, or a related discipline, or equivalent practical experience
- Python or Equivalent Programming Language: Experience building software, applications, scripts, or services in Python or a comparable general-purpose programming language, with the ability and willingness to work in Python
- Familiarity with software development fundamentals, including version control, testing, debugging, and code review
- Practical experience developing, deploying, operating, or troubleshooting software in a Linux environment
- Hands-on experience implementing, integrating, extending, or operating MCP clients, servers, tools, or MCP-based workflows
- Ability to explain how MCP was used to connect an AI system to tools or external systems
- Hands-on experience building an AI agent or LLM-powered workflow that performs meaningful work using tools, APIs, structured workflows, files, databases, or external systems
- Experience should go beyond simple prompt experimentation, basic chatbots, or using an AI assistant to generate text
- Experience building or integrating a RAG workflow that grounds model output in documentation, code, databases, files, or other authoritative information
- Familiarity with ingestion, chunking, embeddings, vector search, metadata, source context, or response evaluation
Desired Qualifications
- Platform architecture and software-system design
- Shell scripting and automation
- CI/CD pipelines and automated validation
- Docker and/or Podman
- REST API development and integration
- Workflow automation across developer or enterprise systems
- FastAPI or a similar Python web framework
- GitHub, Jira, Confluence, Microsoft Teams, or comparable APIs
- PostgreSQL, Redis, or similar data infrastructure
- Agent evaluation, observability, prompt engineering, or model selection
- Embedded systems, firmware, semiconductors, ASICs, or hardware/software integration
- Developer tools, internal platforms, or inner-source engineering
- Microsoft Teams bot development or Power Automate
- Experience operating production services or internal developer platforms
Hiring someone like this?
Get your role in front of qualified candidates on Sorce.