LLM Full Stack Engineer

Job Role - LLM Full Stack Engineer
Location – Remote

Bill rate – $85/hr on C2C.

Expr. Range – 8– 12 years

Must have Skills : Python (Strong), FastAPI (Strong), React (Strong), Next.js, LLM engineering

Job Description :

Must-Have Technical Skills Backend, AI & LLMs

8+ years building backend services and APIs with Python.

2+ years hands-on experience developing and deploying LLM-based systems.

Strong experience with FastAPI or Flask, microservices, Docker, and Kubernetes.

Production experience with LLM APIs and frameworks (OpenAI, Anthropic, LangChain, LlamaIndex).

Strong understanding of RAG architectures, vector databases, and semantic search.

Experience shipping generative AI solutions to production at scale (beyond POCs).

Knowledge of event-driven architectures, messaging systems, and server-side events.

Solid understanding of backend security, authentication, and data protection.

Front-End & Web

5+ years of professional front-end development experience.

Strong hands-on experience with Next.js, React, and TypeScript.

Experience deploying and optimizing applications on Vercel.

Deep understanding of SSR, SSG, performance optimization, and SEO.

Proficiency with modern styling approaches (Tailwind, CSS Modules, Styled Components, Material UI).

Experience with testing frameworks (Jest, React Testing Library, Cypress, or Playwright).

Familiarity with CI/CD pipelines (GitHub Actions, Vercel).

Nice-to-Have Skills –

LLM guardrails, monitoring, and observability tooling.

Edge Functions and Vercel Analytics.

GraphQL (Apollo, Relay).

Internationalization (i18n) in Next.js.

Full-stack experience with Node.js, Express, or relational/NoSQL databases.

Experience building AI solutions in large, business-critical applications