AI-Enabled Full-Stack Engineer

Arkhya Tech. Inc.; Mountain View (CA); On-site; USD 150,000 - 190,000; Full time

Job summary

Arkhya Tech. Inc. is seeking a versatile AI-enabled Full-Stack Engineer to bridge traditional web development with AI.

You will own features end-to-end—from UI and APIs to LLM integration, RAG, and agent workflows. This applied AI role emphasizes rapid, reliable product delivery rather than model training. You will design scalable frontend and backend components, integrate AI tooling, and ensure robust observability, security, and cost containment in production platforms on AWS/Azure/GCP with

Qualifications

• 5+ years of professional full-stack software development experience.
• Hands-on experience integrating LLM APIs, prompt engineering, vector databases, and RAG frameworks.
• Solid understanding of RESTful APIs, relational/NoSQL databases, and cloud-native microservices.
• Hands-on experience with AWS and container orchestration using Kubernetes (K8s).
• Familiarity with AI observability, security guardrails, cost optimization, and evaluation metrics.

Responsibilities

• End-to-end development of scalable web features across frontend and backend stacks.
• Integrate LLM APIs, vector search, and RAG architectures into production flows.
• Build AI agents, manage context windows, and implement MCP interfaces.
• Design for AI reliability, latency constraints, and cost tracking.
• Collaborate with product/design to craft AI-driven UX.
• Containerize and scale services using Docker and Kubernetes on cloud platforms with CI/CD pipelines.

Skills

Full-stack development

LLM integration

RESTful APIs

Cloud-native microservices

Observability & guardrails

Tools

TypeScript

React

Next.js

Python

FastAPI

Java

Spring Boot

Docker

Kubernetes

AWS

Job description

We are looking for a versatile AI-Enabled Full-Stack Engineer to bridge the gap between traditional web development and modern artificial intelligence. You will own features end-to-end — from the user interface and backend APIs to LLM integration, retrieval-augmented generation (RAG), and agent workflows. This is an applied AI role focused on rapid, reliable product delivery rather than foundational model training.

Key Responsibilities

• End-to-End Development: Design and build scalable web features using modern frontend and backend stacks (e.g., TypeScript, React, Next.js, Python, FastAPI, Java, Spring Boot).
• Applied AI Integration: Integrate Large Language Model (LLM) APIs, vector search, and RAG architectures into production user flows.
• Agent & Tool Workflows: Build custom AI agents, manage context windows, and implement structured tool invocation or Model Context Protocol (MCP) interfaces.
• AI Reliability & Guardrails: Design for AI failure modes, latency constraints, token cost tracking, hallucination mitigation, and observability.
• AI-First UX: Collaborate with product and design teams to craft intuitive, responsive, and AI-driven user experiences.
• Production Deployment: Containerize and scale services using Docker and Kubernetes (K8s) on cloud platforms (AWS/Azure/GCP), with automated CI/CD pipelines.

Required Qualifications & Skills

• Experience: 5+ years of professional full-stack software development experience.
• AI/ML Tooling: Hands-on experience integrating LLM APIs, prompt engineering, vector databases, and RAG frameworks.
• System Architecture: Solid understanding of RESTful APIs, relational/NoSQL databases, and cloud-native microservices.
• Cloud & Infrastructure: Hands-on experience with AWS and container orchestration using Kubernetes (K8s), including deploying and scaling production workloads.
• Production Mindset: Familiarity with AI observability, security guardrails, cost optimization, and evaluation metrics.