Senior LLM Engineer

About the role

You will architect and deliver an AI-powered data intelligence platform that allows users to converse with multiple enterprise data sources using natural language. In this capacity, you will own the end to end design of Retrieval Augmented Generation solutions and semantic search layers that connect complex data ecosystems. You will implement robust conversational AI experiences powered by AWS Bedrock, ensuring that generated responses are accurate, contextually relevant, and secure. You will build and maintain scalable AI pipelines that retrieve, process, and synthesize information from structured databases and unstructured documents into a unified chatbot interface. You will translate ambiguous business requirements into resilient technical specifications that balance innovation with operational reliability. You will collaborate closely with product teams and international clients to iterate on features, refine user interactions, and validate that the system meets strict quality standards. You will mentor junior engineers on best practices for prompt engineering, data retrieval strategies, and model integration within cloud environments. You will continuously evaluate emerging techniques in vector search and embeddings to keep the platform at the forefront of generative AI capabilities.

Key facts

What you'll do

Design and implement scalable Retrieval Augmented Generation architectures that connect enterprise data sources with natural language interfaces.

Develop semantic search and vector similarity workflows using embeddings to enable precise and context aware information retrieval.

Build conversational AI experiences on AWS Bedrock, integrating multiple models and orchestration layers to meet business objectives.

Create efficient data ingestion pipelines that transform raw structured and unstructured data into indexed formats suitable for LLM consumption.

Optimize retrieval performance, latency, and cost across cloud services while maintaining high availability and fault tolerance.

Implement guardrails and evaluation frameworks to ensure generated responses remain accurate, safe, and aligned with user expectations.

Collaborate with product managers and international stakeholders to refine user stories, prioritize features, and validate prototypes through testing.

Contribute to architectural decision records, code reviews, and technical documentation that support long term maintainability and scalability.

Experiment with prompt engineering techniques, tool use patterns, and agentic workflows to enhance the capabilities of deployed AI systems.

Monitor production metrics, log analysis, and user feedback to drive iterative improvements and proactive issue resolution.

Partner with data engineering teams to ensure data quality, governance, and compliance requirements are addressed in the AI pipeline design.

Explore and prototype emerging techniques in RAG, tool integration, and multi modal inputs to expand the platform s functional scope.

Support the deployment of models through CI/CD pipelines, infrastructure as code, and automated testing strategies in cloud environments.

Act as a technical leader in defining best practices for prompt templates, retrieval strategies, and evaluation methodologies across the organization.

Requirements

You possess a Bachelor s or Master s degree in Computer Science, Data Science, or a related technical field, or you have equivalent practical experience.

You have professional experience building Generative AI applications, including designing RAG architectures and integrating LLMs into production systems.

You demonstrate strong proficiency in Python or a similar language, with a solid understanding of libraries and frameworks used in AI and data processing.

You have hands on experience with vector search technologies, embedding models, and similarity based retrieval methods.

You are experienced working with cloud platforms, particularly AWS services such as Bedrock, Lambda, S3, and related AI and compute resources.

You show a proven track record of writing clean, maintainable, and well tested code that adheres to software engineering best practices.

You communicate effectively in English, both in written and verbal forms, enabling clear collaboration with international teams and stakeholders.

You have a strong grasp of data structures, algorithms, and software design patterns that apply to scalable and distributed systems.

Nice to have

Experience with additional cloud providers such as Azure or Google Cloud, and their respective AI and machine learning services.

Familiarity with containerization and orchestration tools such as Docker and Kubernetes in AI deployment scenarios.

Knowledge of data governance, privacy regulations, and compliance considerations in AI driven applications.

Experience with monitoring and observability tools tailored to AI pipelines and production machine learning workloads.

Practical notes

This position is fully remote, allowing you to work from São Paulo or any compatible location.

The role operates on a standard professional schedule, requiring availability during overlapping business hours to support global collaboration.

There are no travel requirements associated with this position, and candidates are not expected to relocate for the duration of the engagement.

There are no visa sponsorship or relocation benefits mentioned for this role.

Applications will be reviewed continuously, and the team encourages candidates who meet the core requirements to submit their profiles promptly.