Senior AI Engineer
New
J
JobgetherAI media planning
Based in BrazilFull-TimeSenior
Salary not disclosed
Apply NowOpens the employer's application page
Job Details
- Languages
- Advanced or fluent English communication skills, both written and verbal
- Required Skills
- PythonCI/CDAWS LambdaPrompt Engineering
Requirements
- Bring solid professional experience in AI engineering, machine learning engineering, or software development involving production AI applications.
- Demonstrate strong proficiency in Python, including developing APIs, integrations, and automated tests.
- Have hands-on experience building applications powered by Large Language Models (LLMs).
- Have experience implementing agentic AI workflows.
- Have experience with prompt engineering, LLM orchestration, and structured output generation.
- Have practical experience evaluating LLM outputs, designing testing strategies, and measuring AI application quality.
- Understand LLM limitations, including hallucinations, response variability, and reliability challenges.
- Have experience with AWS services such as Bedrock, Lambda, S3, or CloudWatch, or similar cloud technologies.
- Have strong knowledge of software engineering best practices, CI/CD, and cloud-based application development.
- Have strong analytical, troubleshooting, and problem-solving skills for investigating complex agent behavior.
- Have advanced or fluent English communication skills, written and verbal.
Responsibilities
- Design, develop, and maintain AI agents and LLM-powered applications using Python and AWS services.
- Implement prompt engineering, agent orchestration, structured outputs, and intelligent decision-making workflows.
- Develop evaluation frameworks to measure agent accuracy, reliability, consistency, and performance.
- Establish performance baselines, automated tests, and regression validation processes.
- Implement guardrails and validation mechanisms for AI-generated outputs.
- Build information retrieval, filtering, ranking, and selection strategies using LLMs.
- Investigate and resolve hallucinations, incorrect interpretations, and inconsistent agent responses.
- Develop end-to-end AI features integrating LLMs with backend APIs, document processing, and cloud infrastructure.
- Improve agent observability through execution tracing, session tracking, and production monitoring.
- Optimize LLM performance, latency, and operational costs through experimentation.
View Full Description & ApplyYou'll be redirected to the employer's site
