Master's Fellow – Agents, LLMs, Generative AI, Prompt Engineering

This is a fully remote position, open to applicants in Brazil.

📋 Description

• Comprehend the existing ecosystem of agents, encompassing architecture, tools, logs, memories, execution flows, and human feedback mechanisms;

• Execute at least one current agent from start to finish in a controlled/local environment;

• Outline the entire execution flow of an agent along with its primary interfaces;

• Review the latest advancements in agent memory, human feedback, RAG, preference learning, and RLHF-inspired methodologies;

• Identify potential techniques to convert human feedback into memory or operational guidance that can be reused by agents;

• Conduct local experiments with controlled examples and/or anonymized real-world scenarios;

• Develop a simulation mechanism and logging for human feedback within the agent's execution loop;

• Establish evaluation metrics such as success rate, error reduction, stability, latency, cost, and comparison against a baseline without adaptive memory;

• Integrate the chosen approach into at least one pilot agent within the existing ecosystem;

• Gather and assess real interactions with human feedback;

• Refine the solution based on the results observed;

• Package the solution as a library or a reusable component for other agents;

• Generate technical documentation, usage examples, and a conclusive report outlining results, limitations, and future steps.

⛳️ Requirements

• Education: Master’s degree

• Fields of study: Computer Engineering, Information Systems

• Intermediate-level proficiency in Python

• Fundamental understanding of LLMs, prompts, agents, and utilizing models through APIs

• Familiarity with Git, code organization, and interpreting existing projects

• Capability to manage structured data, logs, JSON, and tables

• Basic SQL knowledge or a willingness to learn swiftly

• Competence in conducting experiments, defining metrics, and comparing methodologies

• Strong written communication skills for creating technical documentation and reports

• Familiarity with development in practical technical environments, including the use of APIs, environment variables, authentication, logs, and service integration

• Experience with agent frameworks such as smolagents, LangChain, LangGraph, CrewAI, AutoGen, or similar

• Understanding of RAG, embeddings, vector search, or semantic memory

• Comprehension of evaluation methods for LLMs, agents, and human-in-the-loop pipelines

• Basic knowledge of reinforcement learning, RLHF, preference learning, or adaptive systems

• Basic understanding of AWS or another cloud platform

• Familiarity with services such as S3, CloudWatch, IAM, Lambda, ECS/ECR, API Gateway, managed databases, Athena, Secrets Manager, Parameter Store, or Amazon Bedrock

• Basic concepts of deployment, observability, logging, permissions, and security in cloud applications

• Interest in AI applications within the legal field.

🏝️ Benefits

• Opportunity to work on cutting-edge AI technologies

• Collaborative and innovative work environment

• Professional development and continuous learning opportunities

• Flexible working hours and remote work options