Senior Full Stack AI Engineer (AI-Native Systems/Claude Code Expert)

Role Overview:

The Senior Full Stack AI Engineer is responsible for designing and building advanced AI-native software systems across the full technology stack. The role combines modern software engineering, AI systems architecture, LLM integration, agentic frameworks, and AI-native development workflows.

This engineer will develop production-grade AI platforms, autonomous agents, intelligent applications, and scalable AI infrastructure while leveraging Claude Code and other AI-native development environments as core engineering tools.

The position requires a developer capable of operating within an AI-augmented engineering workflow, where complex systems are designed, built, analyzed, and optimized using advanced AI coding agents.

Core Responsibilities

AI-Native Application Development

• Design and build production-grade AI applications and intelligent platforms.

• Develop AI copilots, autonomous agents, and AI-driven automation systems.

• Implement scalable architectures for AI-native SaaS and enterprise platforms.

Claude Code–Driven Engineering

• Use Claude Code as a primary development interface for large-scale software engineering.

• Architect systems using AI-assisted reasoning and repository analysis.

• Develop structured prompts and engineering workflows for AI-assisted coding.

• Use Claude Code for:

• system architecture reasoning

• automated debugging and refactoring

• codebase analysis

• documentation generation

• automated test creation

• performance optimization

• Maintain AI-augmented engineering pipelines.

AI Systems & Agent Architecture

• Build agentic systems and multi-agent orchestration frameworks.

• Develop tool-using AI agents capable of interacting with APIs and software systems.

• Design distributed AI services and reasoning pipelines.

• Implement AI orchestration layers.

Technologies may include:

• LangChain

• LangGraph

• CrewAI

• AutoGen

• OpenAI Assistants API

• Anthropic Claude APIs

LLM Engineering

• Integrate large language models into production systems.

• Design and optimize prompt engineering strategies.

• Implement retrieval augmented generation (RAG) architectures.

• Build context management and long-context reasoning pipelines.

• Implement evaluation pipelines for LLM performance.

Technologies may include:

• OpenAI

• Anthropic

• Hugging Face

• vLLM

• TGI

• Ollama

Knowledge Systems & Vector Infrastructure

• Build semantic search and knowledge retrieval systems.

• Design vector embedding pipelines.

• Implement knowledge indexing and AI memory layers.

Technologies may include:

• Pinecone

• Weaviate

• Milvus

• Qdrant

• FAISS

• ElasticSearch

AI Data & Training Pipelines

• Develop pipelines for data ingestion, transformation, and model preparation.

• Work with structured, semi-structured, and unstructured datasets.

• Support model fine-tuning and evaluation workflows.

Technologies may include:

• PyTorch

• TensorFlow

• Hugging Face Transformers

• Ray

• Dask

• Airflow

Frontend Development for AI Applications

• Build modern interfaces for AI-powered software.

• Implement real-time chat, copilots, and AI interaction systems.

• Develop dashboards and visualization systems.

Technologies may include:

• React

• Next.js

• TypeScript

• WebSockets

• GraphQL

Backend & Platform Architecture

• Design APIs and microservices powering AI applications.

• Build scalable backend systems supporting AI workloads.

• Implement event-driven and distributed system architectures.

Technologies may include:

• Python

• Node.js

• FastAPI

• Flask

• Express

• Kafka

• Redis

• gRPC

AI Infrastructure & Deployment

• Deploy AI systems at scale across cloud and hybrid environments.

• Manage GPU-based inference infrastructure.

• Build scalable inference pipelines.

Technologies may include:

• Docker

• Kubernetes

• Terraform

• AWS / Azure / GCP

• GPU orchestration frameworks

• Ray Serve

AI Security & Governance

• Implement secure AI development practices.

• Protect against prompt injection, model abuse, and data leakage.

• Implement model monitoring and governance frameworks.

Technologies may include:

• Guardrails AI

• Prompt security frameworks

• Model monitoring tools

Required Qualifications

• Bachelor's or Master's degree in Computer Science, AI, Machine Learning, or related field.

• 5+ years of software engineering experience.

• 2+ years building production AI systems.

Must Have:

Claude Code

Deep hands-on expertise with Claude Code as a primary engineering interface, including:

• AI-assisted software architecture design

• Large repository analysis

• AI-driven debugging

• Automated test generation

• Prompt-driven development workflows

• Multi-file codebase manipulation

Required Technical Skills

Programming Languages

• Python

• JavaScript / TypeScript

AI Engineering

• LLM integration

• RAG architecture

• AI agent frameworks

• prompt engineering

• model evaluation

Data & Retrieval

• vector databases

• embedding pipelines

• semantic search systems

Infrastructure

• containerization

• distributed systems

• cloud deployment

Preferred Advanced Skills

• multi-agent AI systems

• autonomous development environments

• LLM fine-tuning

• reinforcement learning

• AI reasoning frameworks

• knowledge graph integration

• GPU infrastructure optimization

Key Competencies

• AI-native systems thinking

• strong architectural design capability

• ability to translate AI research into production systems

• strong debugging and performance optimization skills

Success Metrics

• speed and quality of AI-powered development

• successful deployment of scalable AI systems

• effectiveness of AI-assisted engineering workflows

• reliability and performance of AI infrastructure