Software Engineer – Generative AI / LLM

HireRising; Scottsdale (AZ); On-site; USD 120,000 - 190,000; Full time

Job summary

HireRising seeks a hands-on AI Engineer in Scottsdale to build and deploy production-grade Generative AI and agentic AI solutions. You will create LLM-powered applications, AI agents, and multi-agent workflows using Python and FastAPI, with OpenAI, AWS Bedrock, and other GenAI tech.

The role emphasizes RAG pipelines, LLM orchestration, observability, guardrails, and reducing hallucinations, plus deploying scalable services via Kubernetes/OpenShift, Docker, Terraform, and vector databases.

Qualifications

• Hands-on experience with Agentic AI, RAG, and LLM orchestration.
• Experience with LangChain, LangGraph, Semantic Kernel, or similar.
• Experience with AWS Bedrock and cloud-native AI solutions.
• Experience with vector databases and LLM evaluation.
• Strong software engineering and API development experience.

Responsibilities

• Build and deploy LLM-powered applications and AI agents.
• Develop RAG pipelines, orchestration, and enterprise integrations.
• Work with major GenAI providers and cloud services.
• Create AI services and APIs using Python/FastAPI.
• Implement evaluation, guardrails, and reducing hallucinations.
• Deploy scalable AI solutions with Kubernetes, Docker, Terraform.
• Work with MCP, vector databases, embeddings, and fine-tuning.

Skills

Agentic AI

RAG pipelines

LLM orchestration

LangChain

LangGraph

Semantic Kernel

AWS Bedrock

Vector databases

LLM evaluation

API development

Python

Tools

Kubernetes/OpenShift

Docker

Terraform

FastAPI

Job description

We are looking for a hands-on AI Engineer with strong experience building and deploying production-grade Generative AI and Agentic AI solutions.

Key Responsibilities

• Build and deploy LLM-powered applications, AI agents, and multi-agent workflows.
• Develop RAG pipelines, LLM orchestration, and enterprise AI integrations.
• Work with OpenAI, Claude, Gemini, AWS Bedrock, and related GenAI technologies.
• Build AI services and APIs using Python/FastAPI.
• Implement LLM evaluation, observability, guardrails, and hallucination reduction.
• Deploy scalable AI solutions using AWS, Kubernetes/OpenShift, Docker, and Terraform.
• Work with MCP, vector databases, embeddings, and LLM fine-tuning/QLoRA.

Must Have

• Hands-on experience with Agentic AI, RAG, and LLM orchestration.
• Experience with LangChain, LangGraph, Semantic Kernel, or similar.
• Experience with AWS Bedrock and cloud-native AI solutions.
• Experience with vector databases and LLM evaluation.
• Strong software engineering and API development experience.

Ideal candidate: Someone who has built and supported enterprise GenAI platforms in production, not just POCs.