icon Careers

Let's work together.

Full-Stack Developer with Claude / AI Experience

Karachi | Technology

Summary

We are looking for an experienced and forward-thinking Full-Stack Developer with hands-on experience building AI-powered applications using Anthropic’s Claude API. The ideal candidate combines strong engineering fundamentals with a practical understanding of large language models, crafting products that feel genuinely intelligent. This role sits at the intersection of traditional software development and applied AI, working closely with product, design, and data teams to ship meaningful features.

Responsibilities

  • Design, develop, and maintain full-stack web applications using modern JavaScript frameworks (React, Next.js) and backend runtimes (Node.js, PHP, etc.)
  • Integrate and manage Claude API calls, including prompt design, context management, tool use, and streaming responses
  • Build agentic and multi-step AI workflows using Claude’s tool use and function calling capabilities
  • Design scalable RESTful and GraphQL APIs with proper rate limiting, error handling, and observability
  • Implement secure, token-efficient prompt pipelines, managing conversation history, system prompts, and retrieval-augmented generation (RAG)
  • Collaborate with product and design to create intuitive AI-native user experiences
  • Write clean, testable code with attention to performance, security, and maintainability
  • Participate in code reviews, architecture discussions, and sprint planning
  • Stay current with developments in the Claude ecosystem, Anthropic model updates, and the broader LLM landscape

Requirements

Experience:

3+ years of full-stack development, with at least 1 year working on AI or LLM-integrated applications.

Skills & Competencies:
  • Frontend: React, Next.js, TypeScript
  • Backend: Node.js, Php, or Python (FastAPI / Express / NestJS)
  • AI / LLM: Anthropic Claude API, prompt engineering, MCP, Claude Skills, Plugins
  • AI Workflows: Tool use, RAG, agents, streaming
  • Databases: PostgreSQL, MongoDB, Redis
  • Vector / Search: Pinecone, pgvector, or similar
  • APIs: REST, GraphQL, WebSockets
  • Devops: Git, CI/CD, Docker, Vercel / AWS
  • Practical understanding of LLM context windows, token limits, and cost-aware design
  • Experience designing system prompts for consistent, safe, and on-brand AI outputs
  • Familiarity with responsible AI principles, handling sensitive content, avoiding hallucinations, and building in appropriate guardrails
  • Strong communication skills and ability to explain AI capabilities and limitations to non-technical stakeholders
Education:

Bachelor’s degree in Computer Science, Software Engineering, or a related field. Equivalent practical experience is equally valued.

Nice to Have:
  • Experience with other LLM providers (OpenAI, Gemini) and ability to make informed model selection decisions
  • Contributions to open-source AI tooling or published AI-powered projects
  • Familiarity with LangChain, LlamaIndex, or similar orchestration libraries
  • Experience with model evaluation, evals frameworks, or A/B testing AI outputs
  • Portfolio, GitHub, or live demos of AI-powered applications you have shipped