




Job Summary: We are seeking a Mid/Senior-level professional to develop and optimize LLM-based applications, orchestrate agents, and implement AI data architectures while building robust Python APIs. Key Highlights: 1. Application development and AI agent orchestration 2. Robust API development in Python and scalability on AWS Cloud 3. A culture of development, growth, and continuous learning **What We’re Looking For:** A Mid/Senior-level professional experienced in **(Python/Gen AI).** **Responsibilities:** * Develop and optimize Large Language Model (LLM)-based applications, ensuring response quality and prompt efficiency; * Agent Orchestration: Design and implement complex workflows and multi\-agent systems using LangChain and LangGraph for reasoning automation; * AI Data Architecture: Implement Retrieval\-Augmented Generation (RAG) strategies, including vector databases and semantic search indexing techniques; * Backend Development: Build robust and high-performance APIs in Python (FastAPI/Django) to serve large-scale AI models; * Cloud Scalability: Develop and deploy solutions using the AWS ecosystem, focusing on AI services, serverless computing, and containers; * Quality and Monitoring: Establish model testing standards (e.g., hallucination evaluation, latency, cost) and ensure the full development lifecycle (LLMOps). **Requirements:** * Advanced Python: Deep expertise in the language, including concurrency, static typing, and software engineering best practices (SOLID, Clean Code); * AI Frameworks: Solid experience building chains with LangChain and cyclic/graph-based workflows with LangGraph; * LLM Providers: Hands-on experience integrating models via API (OpenAI, Anthropic) and via AWS Bedrock; * Cloud Computing (AWS): Practical knowledge of Lambda, ECS/EKS, S3, and databases (RDS/DynamoDB); * Software Engineering: Proficiency in Git, Docker, and CI/CD pipelines applied to backend projects. **Nice-to-Have:** * LLMOps: Familiarity with model monitoring tools such as LangSmith, Weights \& Biases, or Arize Phoenix; * Fine\-tuning: Understanding of fine-tuning open\-source models (Llama, Mistral) and PEFT/LoRA techniques; * Infrastructure as Code: Experience with Terraform or AWS CDK for provisioning AI environments; * AI Security: Familiarity with prompt injection mitigation and sensitive data protection practices (LGPD). **Behavioral Profile:** We seek a candidate who: * Enjoys teamwork and is **collaborative** in their assignments; * Has the **courage** to challenge themselves and go beyond, embracing new growth opportunities; * Transforms ideas into **creative solutions** and pursues quality in all daily tasks; * Possesses strong **problem-solving skills**; * Is capable and comfortable working independently and **managing their own time**; * Is interested in tackling technologically **adversarial and innovative** situations. Big enough to deliver – small enough to care. **\#VempraGFT** **\#VamosVoarJuntos** **\#ProudToBeGFT** With over 35 years in the market and operations across 16 countries, GFT employs more than 12\.000 people worldwide — including 4\.000 in Brazil. Here, diversity, equity, and inclusion sit at our core, and ensuring a safe workplace for everyone reflects who we are. We foster a culture of development and growth anchored in our Continuous Scaled Learning pillar because we believe intelligent technology use is the key to success in today’s digital world. **What We Offer** -------------------- * Multi\-benefit card – you choose how and where to use it. * Tuition support for undergraduate, graduate, MBA, and language courses. * Certification incentive programs. * Flexible working hours. * Competitive salaries. * Annual performance reviews with structured career development plans. * Opportunities for international career progression. * Wellhub and TotalPass. * Private pension plan. * Childcare allowance. * Medical assistance. * Dental assistance. * Life insurance. \#VemPraGFT


