All the relevant skills, qualifications and experience that a successful applicant will need are listed in the following description.
Locations: Austin, TX | Charlotte, NC | New York, NY | Tempe, AZ | San Diego, CA, (hands on AI)
Role Overview
We are seeking a highly hands-on AI Engineering leader with deep expertise in Generative AI, Agentic systems, and production-grade AI platforms.
This role is not a pure management role — the ideal candidate will actively design, build, and scale AI systems (RAG, agents, evaluation frameworks) while leading engineering initiatives and influencing platform strategy.
The candidate must demonstrate strong AI + AWS cloud expertise, with proven experience delivering enterprise-grade AI solutions in production environments.
Core Responsibilities
AI System Design & Development
Design and build production-grade GenAI systems, including:
Multi-agent architectures
Retrieval-Augmented Generation (RAG) pipelines
GraphRAG implementations
Autonomous agent workflows and orchestration
Develop and integrate AI agents with tools, APIs, and enterprise systems
Implement MCP-based agent communication and tool-use frameworks
Apply advanced prompt engineering techniques for reliability and performance
Agentic AI & Evaluation
Build and deploy multi-agent orchestration systems
Develop and implement:
Agent evaluation frameworks
RAG evaluation pipelines
Measure and optimize:
Output quality
Hallucination rates
Relevance and groundedness
Continuously improve models through evaluation-driven iteration
Engineering & Platform Development
Develop APIs and services using:
Python (primary)
.NET (preferred)
Build scalable AI services with:
REST APIs
Microservices architecture
Contribute to web-based AI applications using:
Angular / TypeScript (preferred)
Integrate AI systems into enterprise workflows and applications
Cloud & Infrastructure (AWS Focus)
Design and deploy AI solutions on AWS, leveraging:
Lambda, S3, EC2, EKS, Glue, SNS, SQS
Kafka-based streaming architectures
Build scalable and secure AI pipelines using cloud-native patterns
Implement cost-efficient and high-performance AI workloads
DevOps & CI/CD
Design and implement CI/CD pipelines using GitHub Actions
Integrate AI workflows into CI/CD pipelines with strong AWS integration
Ensure:
Automated deployment
Testing and validation of AI systems
Continuous monitoring and iteration
AI Development Tooling
Leverage modern AI development tools and ecosystems, including:
Claude (Claude API / Claude Code)
Cursor AI (AI-assisted development workflows)
Build and optimize developer workflows using AI-assisted coding tools
Required Qualifications
10+ years of overall xsgimln engineering experience
5+ years of hands-on AI/ML / GenAI development in production environments
Strong experience building:
AI agents (minimum 2+ implementations)
GraphRAG systems (minimum 2+ implementations)
MCP-based integrations (minimum 1+)
Proven expertise in:
Multi-agent orchestration
RAG pipelines
Agent and RAG evaluation frameworks
Strong programming skills in:
Python (must-have)
Experience with:
API development and system integration
Strong experience with:
AWS cloud platform (must-have)
Preferred Qualifications
Experience with:
.NET / C# development
Terraform (Infrastructure as Code)
Experience building:
Web applications using Angular / TypeScript
Familiarity with:
Kafka-based streaming systems
Exposure to:
Advanced AI orchestration frameworks (LangChain, LangGraph, etc.)