Senior AI Engineer – LLM Agents (Nearshore Brazil)

OpenKrill

United States

On-site

USD 140,000 - 190,000

Full time

14 days+

A complete application in a minute

Tailored resume and cover letter, ready to send.

Get past ATS filters

Benefits offered by this job

Health and dental insurance

Meal and food allowance

Childcare assistance

Extended paternity leave

Wellbeing programs

Life insurance

CI&T University

Language learning platform

Profit Sharing

Job summary

CI&T is seeking an experienced AI Engineer to join our nearshore team, building and evaluating AI agents powered by Large Language Models. You will develop Python applications, orchestrate agent workflows, and deploy intelligent solutions on AWS Bedrock and modern cloud services.

You will implement evaluation frameworks, guardrails, and observability, address hallucinations, latency, and reliability issues, and collaborate with product and engineering to deliver scalable, production‑ready AI

Qualifications

Seasoned AI/ML engineer or software developer with production AI apps experience.
Proficient in Python with API integrations and automated testing.
Hands-on experience building LLM-based applications and agentic AI workflows.
Experience with prompt engineering, LLM orchestration, and structured output generation.

Responsibilities

Design, develop, and maintain AI agents and LLM-powered applications using Python and AWS services.
Develop evaluation frameworks to measure agent accuracy, reliability, and behavioral consistency.
Establish performance baselines, automated tests, and regression validation for agent changes.
Implement guardrails and validation mechanisms for safe AI outputs.
Develop information retrieval, filtering, ranking, and selection strategies with LLMs.
Address hallucinations, misinterpretations, and inconsistent agent responses.
Build end-to-end AI features integrating LLMs with backend APIs and cloud infrastructure.
Improve observability with tracing, session tracking, and production monitoring.
Collaborate with engineering and product teams to deliver scalable, production-ready AI solutions.
Optimize LLM performance, latency, and costs through experiments.