Lead Platform Engineer, Agentic Operations

Nucleus is seeking a Lead Platform Engineer, Agentic Operations , to build AI-powered tools that accelerate software delivery and improve the daily developer experience. This role will create automated PR reviewers, code-quality gates, test-generation capabilities, and codebase-aware agents, integrating them directly into Slack, Git, CI/CD, IDEs, and internal engineering workflows. This lead-level engineer will help set the technical direction for AI-enabled developer tooling while ensuring solutions are reliable, secure, measurable, and widely adopted. If you combine strong software engineering and system-design experience with hands-on AI expertise and a passion for reducing developer toil, we’d love to welcome you aboard. What You Will Do Build and launch AI-powered developer tools that engineers use every day, including automated PR review, code-quality gates, test generation, and codebase-aware agents. Integrate these tools into Slack, Git, CI/CD, IDE, and internal platform workflows so code moves from development to production faster without lowering quality or security. Measure adoption, cycle time, review load, and defects; establish benchmarks and AI evaluation frameworks to assess quality and impact, using data and developer feedback to reduce toil and continuously improve the developer experience. Expectations of Your Experience Required Qualifications: Lead-level software engineering and system design with 8+ years of professional experience building production services, internal platforms, or developer tooling, with strong ownership of architecture, reliability, and technical direction. Advanced proficiency in Python and working proficiency in at least one additional language such as TypeScript/JavaScript or Go. Experience building CI/CD integrations, PR bots and status checks, CLIs, code-analysis pipelines, IDE integrations, or internal developer platforms - not only using AI tools as an end user. Advanced proficiency with the use of containers – Docker and Kubernetes experience. LLM and agent engineering with hands-on experience with prompt and context engineering, structured outputs, tool calling, RAG over codebases, agent workflows, evaluation harnesses, and productionizing AI features. Strong knowledge of GitHub or GitLab APIs, webhooks, branch protection, required checks, custom review comments, risk scoring, and merge policies. Experience combining linting, static analysis, automated testing, changed-code coverage, security scanning, and merge blocking into reliable delivery workflows. Experience in unit, integration, and end-to-end testing; AI-assisted test generation; test-data creation; coverage strategy; flaky-test management; and dependable CI integration. Code quality and application security tooling: Practical experience with tools such as SonarQube, Semgrep, CodeQL, ESLint, Ruff, SAST, dependency scanning, secret detection, supply-chain controls, and policy-as-code. AI evaluation, guardrails, and observability: Ability to build regression suites, model-output quality measures, human-review paths, logging, metrics, tracing, and failure-analysis workflows for AI-powered systems. Impact measurement and technical tool evaluation: Ability to instrument cycle time, review load, defect rates, AI adoption, and developer satisfaction; assess commercial tools; make build-versus-buy decisions; and turn results into priorities and ROI. Systems and product thinking for internal customers — treats other engineers as the product’s users; drives adoption, gathers feedback, iterates, and balances speed vs. Safety/governance. Preferred Qualifications: Direct experience with AI code review or agentic coding tools in production (CodeRabbit, Cursor Bugbot, GitHub Copilot code review, Qodo/PR-Agent, Anthropic Code Review, or similar). Practical use of agent frameworks or orchestration tools (LangChain, LangGraph, LlamaIndex, or custom agent loops). Experience with risk-based or policy-driven automation (auto-approving low-risk PRs, severity scoring, or policy-as-code). Familiarity with observability for developer tools and AI systems (logging, metrics, tracing of AI review outcomes, evaluation dashboards). Prior work measuring developer productivity or DevEx impact (cycle time, review load, AI adoption metrics, or DORA-related instrumentation). Experience operating in regulated or high-compliance environments (security review processes, auditability of AI decisions, or governance of AI-generated code). Knowledge of large monorepos or multi-language codebases and the unique challenges they create for AI tooling. Minimal Requirements 8 Year in technical with a major programming language with a preference to python Must be using AI in their current role or pet project Why You Should Be Excited 100% company-paid health, dental, vision, life, and short-term disability insurance options Generous 401k contribution (not a match) Flexible PTO + 10 company holidays Paid parental leave Fantastic company culture Work on a truly unique, market- defining product Additional Information At Nucleus we are committed to achieving excellence in our field by combining diversity, collaboration, teamwork, and pride in our work. All qualified applicants will receive consideration for employment without regard to race, sex, color, religion, sexual orientation, gender identity, national origin, protected veteran status, or disability.