Senior Fullstack AI Engineer: RAG on Azure Foundry

Conexionhr; Buenos Aires; On-site; ARS 3,200,000 - 5,200,000; Full time

Benefits offered by this job

Ownership of AI features shipped to V1

Direct access to product leadership

Modern Azure stack with experimental预算

Job summary

ConexionHR in Argentina is seeking a Senior Fullstack AI Engineer to design, build and ship production-grade retrieval-augmented generation (RAG) and agentic systems on Azure AI Foundry for our AI products. You will own end-to-end lifecycle of LLM features from ingestion to deployment, collaborating with product, domain experts and client teams to set technical direction.

You will implement agentic workflows, evaluate systems quantitatively and bring features to production with a focus on

Qualifications

• 8+ years of software engineering experience, with 3+ years of hands-on AI/ML and LLM work, including production systems.
• Hands-on RAG experience: chunking, embeddings, vector databases, hybrid retrieval, reranking.
• Experience with Azure AI Foundry and Azure OpenAI Service: deployments, prompt flows, evaluations, cost management.
• Strong Python; comfortable with FastAPI and async programming; containerization (Docker, AKS).
• Experience with at least one orchestration framework: Semantic Kernel, LangChain/LangGraph, LlamaIndex or Autogen.
• Ability to evaluate LLM systems quantitatively and improve them iteratively.
• Solid fundamentals: API design, data modeling, testing, CI/CD, IaC (Bicep/Terraform).
• Experience with sensitive data and security controls in regulated environments.
• Strong written and verbal communication; able to explain trade-offs to non-technical stakeholders.
• Proven full-stack engineer: end-to-end ownership of UI, backend, data, deployment.

Responsibilities

• Design and build RAG pipelines end to end: document ingestion, parsing, chunking, embeddings, hybrid search and reranking.
• Build and operate on Azure AI Foundry: model deployments, prompt flows, Agent Service, AI Search, evaluations and content safety.
• Implement agentic workflows with frameworks such as Semantic Kernel, LangGraph or Autogen.
• Own evaluation: build offline/online eval harnesses, datasets and CI gates.
• Take systems to production: latency/cost optimization, caching, observability, rate limiting, failover.
• Handle sensitive data: PII redaction, RBAC, Key Vault, private networking.
• Collaborate with product/domain experts to ship features.
• Mentor engineers, review designs and code, set standards for prompt engineering and LLMOps.
• Engage in client discussions, architecture reviews and estimates.
• Build full feature surface: backend APIs, data persistence, and front-end interfaces.

Skills

RAG pipelines

Azure AI Foundry

Python

FastAPI

Async programming

Docker

Kubernetes / AKS

Orchestration frameworks

Prompts & LLM evaluation

Security controls

API design

React / TS front-end

REST & GraphQL

CI/CD

Data modeling

Tools

Azure OpenAI Service

Azure AI Foundry

pgvector / vector DBs

Azure Monitor

Terraform / Bicep

Azure DevOps / GitHub Actions

Azure Container Apps

Semantic Kernel

LangChain / LangGraph

Autogen

Job description

ConexionHR in Argentina is seeking a Senior Fullstack AI Engineer to design, build and ship production-grade retrieval-augmented generation (RAG) and agentic systems on Azure AI Foundry for our AI products. You will own end-to-end lifecycle of LLM features from ingestion to deployment, collaborating with product, domain experts and client teams to set technical direction.

You will implement agentic workflows, evaluate systems quantitatively and bring features to production with a focus on