Senior AI Engineer
New
J
JobgetherArtificial Intelligence
BrazilFull-TimeSenior
Salary not disclosed
Apply NowOpens the employer's application page
Job Details
- Required Skills
- DockerPythonSQLMongoDBFastAPICI/CDPrompt EngineeringLLM
Requirements
- Strong programming skills in Python, including modern asynchronous Python development for production services.
- Proven experience building and deploying LLM-powered applications, including AI agents, tool usage, function calling, prompt engineering, retrieval-augmented generation (RAG), and structured outputs.
- Experience working with major LLM providers such as OpenAI, Anthropic, Google, or similar platforms.
- Experience with FastAPI or equivalent modern web frameworks, along with Pydantic and API development practices.
- Understanding of AI evaluation methodologies, including offline evaluations, benchmarking, regression testing, and quality measurement.
- Experience with cloud platforms and containerized environments, including Docker-based deployments.
- Familiarity with production databases such as MongoDB, SQL-based systems, or data platforms.
- Experience with software testing practices, CI/CD workflows, and maintaining reliable production systems.
- Bachelor’s degree or higher in Computer Science, Artificial Intelligence, Engineering, or a related field, or equivalent practical experience.
Responsibilities
- Design, develop, and deliver agentic AI products, including agent identities, reusable skills, tool integrations, and structured outputs within a configurable AI platform.
- Build advanced prompt and context engineering solutions, including system prompt design, data-driven context injection, memory management, and structured response generation.
- Develop and integrate AI tools connected to internal systems, databases, and external platforms using modern agent integration approaches.
- Create and maintain evaluation frameworks, including LLM-as-judge systems, regression benchmarks, quality metrics, and validation processes to ensure trustworthy AI outputs.
- Work with multiple large language model providers, selecting and optimizing models based on quality, latency, reliability, and cost considerations.
- Improve production AI systems through monitoring, observability, performance optimization, and operational best practices.
- Collaborate with software engineers, data teams, and product stakeholders to deliver complete AI solutions aligned with business objectives.
View Full Description & ApplyYou'll be redirected to the employer's site
