AI Development Lead

HRB; Indianapolis (IN); Presencial; USD 180.000 - 240.000; Jornada completa

Descripción de la vacante

HRB is seeking a Lead AI Full-Stack Engineer to define the technical vision and execution strategy for an AI-native platform. You will lead a cross-functional team while remaining hands-on in code, owning end-to-end direction across Java microservices, Python services, and enterprise React frontends.

You will architect AI systems, implement RAG pipelines, and drive best practices for prompt engineering, latency, cost governance, and security on Azure.

Formación

• 7+ years in full-stack engineering with leadership experience.

Responsabilidades

• Technical Leadership & Strategy: Establish end-to-end AI application architecture and set engineering standards.
• Team Mentorship & Delivery: Guide cross-functional engineers, conduct code reviews, map product roadmaps to tech deliverables.
• AI & RAG System Architecture: Design resilient RAG pipelines and multi-agent workflows.
• Full-Stack & Microservices Design: Oversee Java Spring Boot and Python FastAPI/Django microservices with React frontends.
• Enterprise Azure Infrastructure: Own cloud architecture on Azure, including OpenAI services and AKS.
• AI Governance & Reliability: Implement guardrails, safety checks, monitoring, and metrics.

Conocimientos

Leadership

Full-stack engineering

AI-native applications

React/TypeScript

Java/Spring Boot

Python (FastAPI/Django)

Azure cloud

RAG orchestration

LLM governance

Herramientas

LangChain

LlamaIndex

AutoGen

Azure OpenAI

Azure AI Search

AKS

Docker

Kubernetes

Terraform

Bicep

Pinecone

Qdrant

pgvector

Descripción del empleo

Job Summary
We are looking for a Lead AI Full-Stack Engineer to define the technical vision, architecture, and execution strategy for our next-generation AI-native platform. In this high-impact role, you will lead a cross-functional team of developers while remaining hands-on in code.
You will own end-to-end technical direction across our Java and Python Microservices, enterprise React applications, cloud systems (Azure), and advanced LLM/RAG orchestration pipelines.
Key Responsibilities

• Technical Leadership & Strategy: Establish end-to-end AI application architecture, establish best practices for prompt engineering, latency optimization, cost control, and set engineering standards across frontend, backend, and AI stacks.
• Team Mentorship & Delivery: Guide and mentor cross-functional engineers (5–10 team members), conduct code reviews, unblock technical issues, and partner with Product and Design leaders to map product roadmaps into technical deliverables.
• AI & RAG System Architecture: Architect resilient Retrieval-Augmented Generation (RAG) pipelines, multi-agent frameworks, and real-time semantic search using tools like LangChain, LlamaIndex, or AutoGen.
• Full-Stack & Microservices Design: Oversee robust, scalable Microservices engineered in Java (Spring Boot) and Python (FastAPI/Django), integrated with component-driven React/TypeScript frontends.
• Enterprise Azure Infrastructure: Own cloud architecture strategy on Microsoft Azure (Azure OpenAI, Azure AI Search, AKS, Container Apps), prioritizing high availability, strict security protocols, and cost governance.
• AI Governance & Reliability: Implement guardrails for LLM safety, PII detection, fallback mechanisms, hallucination evaluation metrics, and continuous performance monitoring.

Preferred Qualifications

• Experience: 7+ years in full-stack engineering, including 2+ years leading engineering initiatives or technical teams and building AI-native applications in production.
• Frontend: React.js, TypeScript, state management architectures, micro-frontends, and web performance optimization.
• Backend: Mastery of Java (Spring Boot) and Python (FastAPI, Flask); expertise in Microservices design, asynchronous patterns, and API gateways.
• AI / LLM Orchestration: Deep expertise with RAG architectures, Vector DBs (Pinecone, Qdrant, Azure AI Search, pgvector), agentic workflows, model routing, and token optimization.
• Cloud & DevOps: Advanced skills in Azure cloud infrastructure, Docker, Kubernetes (AKS), Infrastructure-as-Code (Terraform/Bicep), and CI/CD automation.
• Leadership: Track record of mentoring developers, driving architectural decisions, and communicating complex AI tradeoffs to executive leadership.
• Proven experience fine-tuning open-source models (Llama, Mistral) or building enterprise-wide semantic caches.
• Experience with multi-agent design patterns (AutoGen, CrewAI) and complex function-calling structures.
• Deep knowledge of enterprise AI compliance, data privacy, and Responsible AI frameworks.