Senior AI Full Stack Engineer

Location: Peachtree City, Georgia | Farmington Hills, Michigan | The Colony, Texas

Employment Type: Full-Time W2 Only

Job Overview

We are seeking a highly skilled Senior AI Full Stack Engineer to design, build, and deploy production-grade AI-powered applications. The ideal candidate is an AI-native engineer with deep expertise in modern web development, Large Language Models (LLMs), Retrieval-Augmented Generation (RAG), agentic AI frameworks, and cloud-native architectures.

This role requires ownership of the complete technology stack—from intuitive React/Next.js user interfaces to scalable FastAPI-based backend services and cloud-deployed AI solutions. You will collaborate with AI Architects, Product Managers, Data Scientists, and UX teams to deliver innovative AI-driven products across connected vehicles, infotainment systems, manufacturing intelligence, and enterprise applications.

Key Responsibilities

AI & Application Development

• Design and develop end-to-end AI-powered applications using React/Next.js, FastAPI/Node.js, and cloud-native technologies.

• Integrate and optimize LLMs including OpenAI GPT, Anthropic Claude, Google Gemini, Meta Llama, Mistral, and similar foundation models.

• Build scalable Retrieval-Augmented Generation (RAG) pipelines, including document ingestion, embedding generation, semantic search, and vector database management.

• Develop agentic AI systems using frameworks such as LangChain, LangGraph, CrewAI, AutoGen, LlamaIndex, or OpenAI Agents SDK.

• Implement prompt engineering, context management, tool-calling workflows, and structured output validation.

Backend & Cloud Engineering

• Build high-performance APIs and microservices using FastAPI, Python, Node.js, and event-driven architectures.

• Design distributed systems leveraging Kafka, Redis, asynchronous queues, and fault-tolerant processing patterns.

• Develop and maintain cloud-native applications on AWS, Azure, or Google Cloud Platform.

• Deploy containerized applications using Docker, Kubernetes, and Helm.

Front-End Development

• Build responsive, high-performance web applications using React, Next.js, TypeScript, and modern UI frameworks.

• Develop conversational AI interfaces with real-time streaming responses using WebSockets and Server-Sent Events (SSE).

• Create AI-assisted dashboards, multi-modal user experiences, and intelligent workflow applications.

AI Governance & Observability

• Implement AI guardrails, hallucination mitigation, content filtering, PII protection, audit logging, and compliance controls.

• Establish monitoring and observability frameworks for AI systems, including latency tracking, token usage monitoring, model performance analysis, and quality evaluation.

• Utilize tools such as LangSmith, Arize, Helicone, Weights & Biases, OpenTelemetry, Prometheus, Grafana, and Datadog.

Engineering Excellence

• Participate in architecture reviews, code reviews, and technical design discussions.

• Implement automated testing strategies including unit, integration, performance, and AI evaluation testing.

• Build and maintain CI/CD pipelines supporting AI-enabled applications and zero-downtime deployments.

• Mentor engineering teams and promote best practices across software development and AI engineering.

Required Qualifications

• Bachelor''s degree in Computer Science, Software Engineering, or a related technical discipline. Master''s degree preferred.

• 10+ years of Full Stack Software Engineering experience

• Minimum 4+ years of hands-on experience building and deploying production AI/LLM-powered applications.

• Proven experience delivering AI products used by real customers at scale.

Front-End Expertise

• Expert-level experience with React.js and Next.js.

• Strong proficiency in TypeScript.

• Experience with SSR, SSG, App Router, and streaming architectures.

• Expertise in state management tools such as Redux Toolkit, Zustand, or Jotai.

• Strong understanding of modern CSS frameworks and UI component libraries.

Backend Expertise

• Strong Python development experience using FastAPI.

• Experience building scalable REST APIs and streaming services.

• Expertise in microservices architecture and distributed systems.

AI & Machine Learning Expertise

• Hands-on experience integrating OpenAI, Anthropic Claude, Gemini, Llama, Mistral, or similar LLMs.

• Deep understanding of RAG architectures and vector databases including Pinecone, Weaviate, Chroma, Qdrant, and pgvector.

• Experience with LangChain, LangGraph, LlamaIndex, CrewAI, AutoGen, or OpenAI Agents SDK.

• Strong prompt engineering and context engineering expertise.

• Experience implementing AI guardrails, hallucination prevention, and output validation.

Database & Infrastructure

• Strong experience with PostgreSQL, MongoDB, and Redis.

• Experience with Docker, Kubernetes, Helm, and cloud-native deployments.

• Experience working with AWS, Azure, or Google Cloud Platform.

• Familiarity with managed AI services such as AWS Bedrock, Azure OpenAI, or Vertex AI.

Observability & DevOps

• Experience with CI/CD pipelines and automated testing frameworks.

• Hands-on experience with AI observability tools including LangSmith, Arize, Helicone, or Weights & Biases.

• Familiarity with OpenTelemetry, Prometheus, Grafana, Datadog, and distributed tracing tools.

Preferred Experience

• Automotive industry experience, including Connected Vehicles, IVI (In-Vehicle Infotainment), Telematics, Manufacturing Intelligence, or Supply Chain Optimization.

• Experience building enterprise-scale AI applications supporting large user bases.

• Exposure to multimodal AI systems, autonomous agents, and AI-driven workflow automation.

Regards,

Suchitra

TAM @ SDH SYSTEMS