Senior Fullstack AI Engineer: RAG & Azure Foundry Lead

Conexion HR; United States; Remote; USD 180,000 - 260,000; Full time

Job summary

Conexion HR is seeking a Senior Fullstack AI Engineer to design, build and ship production-grade RAG and agentic systems on Azure AI Foundry for our AI products. You will own end-to-end LLM feature lifecycles, from ingestion and chunking pipelines to vector and hybrid search, prompts and orchestration, evaluation and deployment.

You will collaborate with product, domain experts and client engineering teams, set technical direction for engineers, mentor peers and drive practical, scalable

Qualifications

• .8+ years of software engineering with 3+ years AI/ML and LLM production work.
• Hands-on RAG experience with embeddings, vector databases and hybrid search.
• Proven Azure AI Foundry and Azure OpenAI Service experience.
• Strong Python and experience with FastAPI and containerization.
• Experience with orchestration frameworks (Semantic Kernel, LangChain, LangGraph, or Autogen).
• CI/CD, IaC and security controls in regulated environments.

Responsibilities

• Design and build end-to-end RAG pipelines including ingestion, parsing and chunking.
• Implement and deploy on Azure services: model deployments, prompt flows, evaluation and content filters.
• Build agentic workflows with tool calling and multi-step planning.
• Develop offline and online eval harnesses and regression gates in CI.
• Bring systems to production: latency/cost optimization, caching and observability.
• Handle sensitive data with RBAC, PII redaction and private networking.
• Collaborate with product and domain experts to ship features.
• Mentor engineers and set LLMOps standards across teams.

Skills

LLM systems design

Python

FastAPI

Docker

Azure OpenAI

Azure AI Foundry

Tools

Azure AI Foundry

Azure OpenAI Service

Semantic Kernel

LangChain

LangGraph

Autogen

Job description

Conexion HR is seeking a Senior Fullstack AI Engineer to design, build and ship production-grade RAG and agentic systems on Azure AI Foundry for our AI products. You will own end-to-end LLM feature lifecycles, from ingestion and chunking pipelines to vector and hybrid search, prompts and orchestration, evaluation and deployment.

You will collaborate with product, domain experts and client engineering teams, set technical direction for engineers, mentor peers and drive practical, scalable