Artificial Intelligence Analyst, Mid-Level

Instituto Hardware BR HBR

. Design, develop, and enhance end-to-end RAG pipelines, including ingestion, chunking, tokenization, embeddings, semantic/hybrid search, reranking, and response generation.

Posted 10/6/2026full-timeRemote • BrazilMid-LevelSeniorWebsite

Core Competencies

Role fit

Core Competencies

Use this summary to align your resume positioning with the role.

Demonstrates expertise in designing and developing end-to-end RAG pipelines and LLM-based applications, with a strong focus on data governance, compliance, and performance evaluation. Proficient in implementing ETL/ELT processes and managing various database technologies to ensure data integrity and accessibility.

Highest-signal resume keywords

RAG Pipeline DevelopmentLLM-Based Application MaintenancePython ProgrammingETL/ELT ProcessesMLOps/LLMOps

ATS Keywords

Tailor your resume

Applicant Tracking System Keywords

Tip: use these terms in your resume and cover letter to boost ATS matches.

Hard Skills

PythonSQLNLPEmbeddingsHugging Face TransformersPyTorchSemantic SearchVector DatabasesData GovernanceData Lineage

Tools & Technologies

DockerKubernetesGitCI/CDAWSGCPAzure

Industry Keywords

Data ProtectionLGPD ComplianceAnonymizationAuthenticationAuthorization

Tech Stack

Tools & technologies

AWSAzureDockerETLGoogle Cloud PlatformGRPCKubernetesNoSQLPythonPyTorchSQL

About the role

Key responsibilities & impact

Design, develop, and enhance end-to-end RAG pipelines, including ingestion, chunking, tokenization, embeddings, semantic/hybrid search, reranking, and response generation.
Build ETL/ELT processes for structured and unstructured sources, with incremental updates, quality validation, and anonymization/masking of sensitive data.
Manage the generation, storage, updating, and versioning of embeddings, integrating vector, relational, and NoSQL databases.
Implement continuous evaluation of LLMs and RAG systems, measuring retrieval, groundedness, hallucinations, latency, and cost.
Monitor quality, latency, availability, cost, and resource consumption in production; automate deployment, versioning, and rollback through CI/CD.
Version prompts, models, datasets, embeddings, and pipelines, ensuring data lineage, auditing, and observability.
Design versioned prompts, system prompts, structured outputs, and tool calling.
Deliver services through REST/gRPC APIs and microservices running on Docker and Kubernetes.

Requirements

What you’ll need

Bachelor’s degree in Computer Science/Engineering, Software Engineering, Data Science, Information Systems, Electrical Engineering, or a related field.
Practical experience building and maintaining LLM-based applications and RAG architectures in production environments.
Python and SQL; frameworks such as Hugging Face Transformers, PyTorch, or equivalent technologies; NLP and embeddings.
Vector databases, semantic search, SQL/NoSQL databases, and ETL/ELT.
MLOps/LLMOps, Git, CI/CD, Docker, Kubernetes, and at least one cloud platform (AWS, GCP, or Azure).
Data governance, data lineage, anonymization, authentication/authorization, and compliance with Brazil’s LGPD data protection law.
Intermediate English (for reading technical documentation and scientific papers).

Benefits

Comp & perks

Medical insurance
Dental insurance
Flexible working hours
Life insurance
Meal allowance
Fuel allowance
Birthday day off
Maternity and paternity benefits
Marriage benefit
Wellhub (Gympass)
Conexa Saúde – Caju Mais