We're looking for a talented and versatile Senior AI/ML Developer with strong experience building GenAI applications, AI agents, and Python-based applications to join our team. In this role, you'll take ownership of AI and software solutions from design through production, with a focus on agentic applications, LLM integrations, evaluation, APIs, and scalable application architecture. You'll work closely with product managers, engineers, QA, and other stakeholders to design, build, test, and deploy solutions for our clients. If you're passionate about AI, building practical LLM-powered applications, scalable software, and using modern AI frameworks to solve complex problems, we'd love to hear from you.
We are 100% remote, but candidates must reside in and be authorized to work in Costa Rica.
Responsibilities:
Design, build, test, and maintain GenAI applications, AI agents, and agentic workflows using Python and modern AI frameworks.
Build and deploy AI agents using frameworks such as Strands and AWS Bedrock AgentCore.
Design and implement LLM-powered applications using appropriate model selection, RAG architectures, vector databases, and knowledge bases.
Develop and maintain APIs and backend services using Python, including RESTful APIs and microservice architectures.
Develop prompt engineering strategies and evaluate LLM and agent responses using appropriate evaluation frameworks, metrics, and testing methods.
Design and maintain document processing and data workflows, including PDF extraction, document transformation, structured output generation, and computer vision-based processing.
Build and maintain knowledge bases and vector database implementations to support AI applications and retrieval workflows.
Optimize AI and application architectures for performance, including reducing system latency and managing infrastructure and model costs.
Implement secure authentication and authorization for APIs, services, and application integrations.
Contribute to CI/CD pipelines, automated testing, monitoring, logging, deployment, and production support.
Troubleshoot complex issues across AI applications, agents, APIs, integrations, data workflows, and supporting infrastructure.
Work with cross-functional teams to understand business requirements, evaluate technical approaches, and deliver reliable AI-powered solutions.
Qualifications:
5+ years of professional software development experience, with strong experience in Python.
Hands-on experience developing GenAI applications, LLM-powered applications, or AI agents.
Strong experience with Python, API design, RESTful APIs, and backend application development.
Experience building and deploying AI agents using agentic frameworks, particularly Strands.
Experience with AWS Bedrock AgentCore or similar platforms for deploying and managing AI agents.
Strong understanding of LLM application patterns, including model selection, RAG architecture, prompt engineering, and vector databases.
Experience with LLM response evaluation, including evaluation frameworks, metrics, testing strategies, and evaluation methods.
Experience building knowledge bases and document processing pipelines, including PDF extraction, document transformation, or similar workflows.
Experience with vector databases and integrating retrieval capabilities into AI applications.
Experience with microservices architectures, secure authentication and authorization, and application integrations.
Experience maintaining CI/CD pipelines and implementing automated testing and deployment practices.
Experience with monitoring and logging solutions for application performance, troubleshooting, and production support.
Experience optimizing application or AI system performance, including latency and cost efficiency.
Strong problem-solving skills, with the ability to understand complex technical systems and make sound engineering decisions.
Strong communication and collaboration skills and the ability to work effectively in an Agile, cross-functional environment.
Ability to work independently, take ownership of complex initiatives, and continuously learn new AI and software engineering technologies.
Nice to Have:
Experience with AWS services used to build and deploy AI applications.
Experience with computer vision, image processing, or curve digitization.
Experience with advanced document processing and data extraction workflows.
Experience building production-grade AI agents and multi-agent systems.
Experience with AI evaluation platforms or custom evaluation frameworks.
Experience modernizing existing applications or integrating AI capabilities into established software systems.
Benefits:
This is a full-time position with the following benefits:
Competitive Base Salary - Great work deserves great pay. Our salaries cover a 40-hour work week, and we also offer optional paid overtime for this position.
Optional Paid Overtime - At JBS, overtime is never required, but if you choose to work additional hours beyond 40 in a week, those hours are compensated at an overtime rate. The decision to take on extra work is entirely employee-driven; we respect your time and encourage a balance that works best for you.
Private Health Insurance - In addition to CCSS coverage, we provide private medical insurance to give you faster access to care and expanded provider options for you.
Paid Time Off - Take the time you need to rest and recharge. We provide paid vacation plus paid public holidays.
Fully Remote - We’ve always been (and always will be) 100% remote.
All JBS roles are fully compliant with Costa Rican labor law, including but not limited to:
CCSS Enrollment (Caja Costarricense de Seguro Social). This ensures access to Costa Rica’s national healthcare system, disability coverage, and pension benefits.
Aguinaldo (13th Month Bonus) - Employees receive the legally required annual Aguinaldo bonus, paid in December.
This is a full-time position with the following benefits
Design and implement production-ready AI agents, prompt-based solutions, and automated workflows for customer-service and payment processes, using Python and Azure Databricks while evaluating quality and reliability.
Build autonomous AI agents for executive workflows, define evaluation systems that measure task quality, and investigate failures to improve reliability before capabilities reach users.
Build and deploy AI systems, including multi-agent workflows and LLM-powered applications, while integrating models into cloud services and developing prompt strategies for client projects.
Designs and implements generative AI solutions for customer environments, taking LLM, RAG, and agent-based systems from prototypes to scalable production integrations across cloud platforms and business processes.
Desenvolve e mantém aplicações mobile escaláveis e de alta performance com Flutter, integrando serviços de IA generativa, agentes e soluções RAG, além de contribuir para arquitetura, APIs e pipelines de CI/CD.
