Especialista de IA in Brazil, Indiana at Jobgether
Explore Related Opportunities
Job Description
This position is posted by Jobgether on behalf of a partner company. We are currently looking for an Especialista de IA in Brazil.
This is a high-impact role at the forefront of applied artificial intelligence, focused on designing and delivering next-generation AI systems powered by LLMs, RAG architectures, and multi-agent frameworks. You will play a key part in building scalable, production-grade solutions that transform how enterprises leverage knowledge, automation, and intelligent workflows. Working in a highly collaborative and innovation-driven environment, you will contribute to architecture decisions, hands-on development, and the evolution of AI platforms in real-world applications. The role requires strong technical depth, systems thinking, and the ability to turn complex business challenges into robust AI solutions. You will work across multidisciplinary teams, shaping both strategy and implementation. This is an opportunity to operate at the intersection of AI research, engineering excellence, and large-scale production systems.
- Design and implement advanced AI solutions leveraging LLMs, RAG pipelines, and multi-agent architectures, ensuring scalability, reliability, and business alignment.
- Develop and optimize retrieval systems using techniques such as hybrid search, multi-query strategies, reranking, and GraphRAG to improve semantic accuracy and performance.
- Build and orchestrate agent-based systems using Agent-to-Agent (A2A) communication models and integrate tools and data sources via Model Context Protocol (MCP).
- Implement embeddings, chunking strategies, and vector search pipelines using tools like Pinecone, FAISS, ChromaDB, or Vertex AI Vector Search.
- Develop backend services and APIs to support AI workloads, ensuring performance, observability, and resilience in distributed environments.
- Work with cloud platforms (preferably GCP), leveraging services such as Vertex AI, BigQuery, and Spanner for scalable AI deployments.
- Apply spec-driven development principles to translate business requirements into executable technical specifications.
- Collaborate with cross-functional teams to define architecture, enforce engineering best practices, and ensure production readiness of AI systems.
- Integrate AI-assisted development tools to improve productivity and accelerate solution delivery.
This role requires strong hands-on experience in AI systems engineering, with deep expertise in LLM-based architectures and production-grade AI solutions. You should be comfortable working across backend engineering, distributed systems, and modern AI frameworks, with the ability to operate both strategically and hands-on.
- Strong experience designing AI architectures using LLMs, RAG, and multi-agent systems.
- Advanced knowledge of retrieval techniques including hybrid search, reranking, multi-query systems, and GraphRAG.
- Experience building and orchestrating AI agents and working with A2A architectures and MCP integration.
- Strong proficiency in Python for AI development, automation, and backend engineering.
- Experience with vector databases such as Pinecone, FAISS, ChromaDB, or similar technologies.
- Solid understanding of embeddings, semantic search, and retrieval pipeline optimization.
- Experience with distributed systems, messaging systems, observability, and scalable architectures.
- Hands-on experience with cloud environments, preferably Google Cloud Platform (Vertex AI, BigQuery, Spanner).
- Familiarity with backend API development for AI-driven applications.
- Experience using AI-assisted development tools and modern engineering workflows.
- Strong problem-solving skills, system design capability, and ability to work in complex technical environments.
- Excellent communication skills and ability to collaborate with cross-functional teams.
Nice to have:
- Experience with regulated environments (fintech, banking, or public sector) and compliance requirements such as LGPD.
- Contributions to open source, research, or production-scale AI agent systems.
- Experience deploying AI agents at scale with measurable performance metrics (latency, cost, quality).
- Competitive compensation aligned with senior AI engineering roles
- Remote-first or hybrid flexibility depending on location and project
- Health and dental insurance coverage
- Meal or food allowance
- Access to learning platforms, certifications, and continuous training programs
- Career development support, mentoring, and technical growth opportunities
- Discounts and corporate benefits programs
- Wellness and lifestyle support initiatives
- Exposure to cutting-edge AI projects and enterprise-scale systems.