Senior AI Engineer

AI Engineer | Location: Remote

Mandatory Skills Claude AI models (Haiku, Sonnet and Opus) in agentic workflows and development activities

Job Description

As killed Agentic Full Stack Developer to build and deploy production-grade applications that harness the power of Claude AI models (Haiku, Sonnet and Opus) in agentic workflows and development activities

Roles & Responsibilities

Must Have-

Required-Design and develop full stack applications that seamlessly integrate Claude models (Haiku 4.x, Sonnet 4.x, Opus 4.x) in agents capable of multi-step reasoning and contextual task execution

Architect scalable agentic systems that leverage Claude's advanced thinking, tool use, and computer use capabilities

Build resilient backend services and APIs that orchestrate agent workflows, manage context windows, and handle asynchronous AI operations

Develop responsive frontend interfaces that surface agent reasoning processes and enable effective human-AI collaboration

Implement production deployment pipelines with monitoring, error handling, and graceful degradation

Establish quality assurance processes including comprehensive testing of non-deterministic AI behaviors

Optimize prompt engineering, context management, and token utilization to maximize efficiency and accuracy in production workloads.

Ensure security best practices around API key management, data privacy, and model output validation

5+ years full stack development experience with modern frameworks (React/Next.js, Node.js/Python, etc.)

Demonstrated experience building applications with Claude Code (Sonnet/Opus) in production environments

Strong understanding of agentic AI patterns: tool use, multi-step planning, self-correction, and autonomous decision-making

Experience with cloud deployment (AWS, GCP, Azure) and containerization (Docker, Kubernetes)

Proficiency in API design, database management, and scalable architecture patterns

Track record of shipping high-quality, well-tested code with attention to edge cases

Understanding of LLM limitations, prompt injection risks, and AI safety considerations

Good to Have-

Experience with Anthropic's APIs and Claude Code

Familiarity with agent frameworks and orchestration tools

Background in prompt engineering and systematic evaluation of LLM outputs

Experience with CI/CD pipelines and infrastructure-as-code