Senior Full-Stack Engineer - LLM-Powered Code Review PoC
At a glance
Senior AI Engineering role at Fuku. San Francisco · full-time · no salary stated · we estimate $205,000–$277,500.
Fuku has not published a salary for this role. The figure below is our estimate, not theirs.
aimlroles summary, based on the employer's posting.
What you'll do
- Build a full-stack prototype that uses LLM APIs to review code and connects with existing CI/CD workflows
- Set up GitHub or GitLab webhooks so pull requests are sent for review automatically
- Combine model reasoning and static checks to find bugs, security risks and code quality issues
- Create repository-specific review rules and a dashboard for statistics, trends and useful next steps
- Package the system with Docker and handle its design, deployment and documentation
What you bring
- At least five years of professional full-stack development work
- You have integrated LLM APIs into production software and connected applications to CI/CD pipelines
- You have built code review, linting or static analysis systems
- You can work across backend and frontend development, using the listed language and framework options
Who this fits
This suits a senior engineer comfortable owning a prototype from architecture through delivery and working independently across the stack. The engagement is contract-based rather than a full-time employee role, and remote work is possible, with a preference for San Francisco Bay Area candidates.
From the employer
NexaFlow is building a next-generation code review tool powered by large language models. We are seeking a Senior Full-Stack Engineer to lead the development of a proof-of-concept prototype that integrates LLM-based analysis into existing CI/CD workflows.
Responsibilities:
- Design and implement a full-stack application that integrates LLM APIs (OpenAI/Anthropic) for automated code review.
- Build webhook-based integrations with GitHub/GitLab to automatically analyze pull requests.
- Develop a hybrid analysis pipeline combining LLM reasoning with static analysis for bug detection, security vulnerability identification, and code quality enforcement.
- Create a configurable rule engine allowing per-repository custom review policies.
- Build a dashboard displaying review statistics, trends, and actionable insights.
- Containerize the entire solution with Docker for easy self-hosted deployment.
- Own the full lifecycle from architecture design through deployment and documentation.
Requirements:
- 5+ years of professional full-stack development experience.
- Strong experience integrating LLM APIs (OpenAI GPT-4, Anthropic Claude) into production systems.
- Hands-on experience with CI/CD pipeline integration (GitHub Actions, GitLab CI).
- Prior work building code review tools, linters, or static analysis systems.
- Proficiency in Python (FastAPI) or Node.js for backend; React or Vue for frontend.
- Experience with Docker containerization and self-hosted deployment.
- Ability to work independently across the full stack from architecture to deployment.
- Strong communication skills for async collaboration.
Nice to Have:
- Experience with RAG (Retrieval-Augmented Generation) architectures.
- Familiarity with CodeQL, Semgrep, or similar static analysis tools.
- Previous startup or PoC-stage project experience.
- Contributions to open-source developer tools.
Additional Information:
- This is a contract/consulting engagement, not a full-time employee role.
- We value flexibility and outcome-driven collaboration.
- Remote-friendly with a preference for candidates in the San Francisco Bay Area.