GenAI Engineer

Designation - GenAI Engineer, Agentic AI Engineer, ML Engineer, Forward Deployment Engineer, AI Consultant, etc

Remote / Contractual Role -1 Year

Okay to use own laptop

Shift PST/ CST

Apply –[email removed]

Must key Point Area

Senior, hands-on GenAI/Agentic AI engineer, not just an architect or consultant.

• Must have personally taken a RAG, agentic AI, chatbot, or similar GenAI system from design through go-live.
• Must have operated and supported the solution in a live production environment at meaningful scale, ideally 500K–1M+ users.
• Should have hands-on ownership across architecture/design, model selection, implementation/coding, testing, deployment, optimization, and production support.
• POC/prototype experience alone is not sufficient.
• proven hands-on, large-scale production delivery experience.

Responsibilities

• Hands-on end-to-end Agentic RAG development: Built, deployed, and operated production-grade Agentic RAG systems, including retrieval pipelines, orchestration, evaluation, monitoring, and optimization.
• Production LLM application experience: Designed, developed, and shipped customer-facing GenAI features using Amazon Bedrock, OpenAI, Azure OpenAI, or Vertex AI, including agents, tool calling, guardrails, and multi-turn conversational assistants.
• Strong Backend & AWS Engineering: 5+ years of software engineering experience with TypeScript, Node.js, AWS Lambda, API Gateway, DynamoDB, CDK/Terraform, CI/CD, automated testing, and scalable cloud architectures.
• AI Coding Assistant expertise: Daily hands-on use of Kiro, GitHub Copilot, or similar AI development tools for software development, with disciplined code review and production engineering practices.
• Production Ownership: Experience owning solutions end-to-end—requirements, architecture, implementation, testing, deployment, observability, performance tuning, cost optimization, security, and ongoing operations.
• Real-world Engineering Depth: Demonstrated experience building reliable, secure, and scalable AI systems in production—not just prompt engineering or proof-of-concepts—with strong understanding of LLM evaluation, model quality, and software engineering best practices.