Senior Backend Engineer – AI Platform

About the Role As a Senior Backend Engineer on the AI Platform team , you will develop high-impact platforms, autonomous agents, and tools designed specifically for our internal software developers and researchers. Our team serves as the company’s focal point and center of excellence for AI innovation - acting as "developers for developers" across both internet-connected and air-gapped environments to automate engineering workflows and accelerate delivery. We partner closely with R&D teams to understand their workflows, gather requirements, and architect the right technical solutions. In this role, you will be a pioneer of modern AI-first engineering workflows. Rather than manually writing routine boilerplate, you will develop tools while utilizing cutting-edge coding harnesses as your primary force multiplier. You will navigate the broader ecosystem, including plugin marketplaces, mods, and custom tool extensions while directing system architecture, evaluating technical trade-offs, and ensuring production-grade code quality. You will tackle engineering challenges ranging from building autonomous CI/CD agents to evaluating, porting, and deploying the latest open-source AI tooling into secured networks. Key Responsibilities Architect & Build Developer Platforms: Design, develop, implement, and scale backend services and developer platforms that integrate LLMs and autonomous agents directly into everyday engineering workflows across connected and isolated environments. Build Autonomous Coding & Review Agents: Develop event-driven automations (e.g., triggering bots via GitLab/GitHub issues and merge requests) powered by Claude Code, Codex, or any other agent harnesses to handle automated code reviews and end-to-end feature implementations. Evaluate & Port Open-Source AI Tooling: Actively research emerging open-source AI tooling including solutions (e.g. Onyx and Open WebUI ) for enterprise RAG and document/data-source chat, open-source OCR engines (e.g. Surya , Marker , PaddleOCR ) for document parsing, and observability platforms (e.g. Langfuse and Opik ). Conduct trade-off analyses, lead technical proofs-of-concept, and adapt these tools for air-gapped deployment. Bridge Connected & Air-Gapped Environments: Solve distribution, packaging, dependency management, and containerization challenges required to take modern tools from internet-connected environments and deploy them reliably in air-gapped networks. Act as the AI Engineering Focal Point: Serve as the central knowledge authority for internal R&D teams, advising them on adopting agent harnesses, plugins, and custom extensions while establishing company-wide best practices for architecture, edge-case handling, and code verification. Requirements Backend Expertise: 5+ years of professional backend development experience designing, building, and operating robust, scalable systems and architectures. Core Language: Strong expertise in Python and modern backend architecture. Core Tooling & OS: Strong proficiency in Linux environments and Git version control workflows. LLM Harnesses & Ecosystem: Hands-on experience developing with modern AI coding harnesses and agentic tools (e.g., Claude Code, Codex), along with familiarity with their ecosystems (plugin marketplaces, mods, extensions) and SDK integrations (e.g., Claude SDK). AI-Accelerated Engineering Mindset: An intuitive ability to drive LLMs to produce production-grade code, combined with the architectural depth to audit, guide, and correct model outputs. Containerization: Solid working experience with Docker and Docker Compose. Collaborative & Product-Oriented: Strong team player with high empathy for internal developer pain points and the ability to translate ambiguous requirements into clean, resilient platform solutions. Advantages B.Sc. in Computer Science, Software Engineering, or a closely related technical field. Experience building and maintaining CI/CD pipelines (GitLab CI, GitHub Actions) and configuration automation (e.g., Ansible). Familiarity with AI orchestration frameworks (e.g., LangChain, LlamaIndex). Experience in packaging, containerizing, or managing infrastructure in on-premises environments. Hands-on experience with open-source RAG, vector databases, or enterprise search platforms. Experience with LLM observability, tracing, and evaluation tools (e.g., Langfuse).