Disclaimer – Must read: Commitment & FocusThis role requires full-time dedication, with clear priority given to Darwoft projects during the established working hours.
It is not compatible with other full-time professional engagements.
Any additional professional activities must be disclosed in advance and must not interfere with the responsibilities or working hours of this role.About DarwoftDarwoft is a software factory that develops custom software solutions and provides IT staff augmentation services for international clients, primarily in the United States and Latin America.
We partner with startups and high-growth companies to build high-impact digital products.
Our culture is people-first, focused on technical quality, long-term relationships, and a collaborative mindset.
We combine technical excellence with human proximity.Senior AI Engineer (Agentic Systems & LLMs) | Contractor GlobalGeneral InformationLocation: Remote (Global)Contract Type: ContractorIndustry / Project: Fintech / Conversational AI & Agentic WorkflowsTime Zone: Coordination with US / LATAM / General teamsEnglish Level: Advanced (C1)About the RoleWe are seeking a Senior AI Engineer specializing in LLMs and agentic architectures to join our core engineering team.
In this role, you will be responsible for designing, building, and deploying end-to-end AI agents that integrate directly into business ecosystems to deliver tangible value.
You will act as a subject matter expert on the latest generative AI advancements, establishing rigorous evaluation pipelines and optimizing prompt engineering, RAG, and tool connections for accuracy, speed, and cost efficiency.ResponsibilitiesAgent Development & Deployment: Design, build, test, and deploy robust, stateful, and scalable AI agents using Python and modern frameworks (Google ADK, LangChain, LlamaIndex, CrewAI, OpenAI SDK, etc.).
End-to-End System Integration: Connect AI agents seamlessly with diverse data sources,



internal services, and external APIs to deliver complete, high-value workflows.LLM Evaluation & Optimization: Design and implement rigorous evaluation pipelines for LLM-powered agents, driving continuous testing and performance monitoring focused on accuracy, response speed, and cost efficiency.Prompt Engineering & Custom Tooling: Apply advanced prompt engineering techniques and develop custom tools, Retrieval-Augmented Generation (RAG) architectures, and vector search systems to ensure grounded, reliable performance.Technical Scrutiny & Leadership: Act as a subject matter expert on generative AI advancements, best practices, and protocols, guiding technical decisions across the agentic lifecycle.RequirementsMust-Have:5+ years of experience in software engineering, with at least 1-2 years dedicated to building and deploying production-grade AI/ML applications focused on LLMs or generative AI.Technical Mastery: Expertise in Python and deep hands-on familiarity with core LLM APIs and frameworks (OpenAI SDK, Google AI SDK, CrewAI, LangChain, LlamaIndex, etc.).
Agentic Systems & AI Architecture: Proven experience implementing agentic workflows, including RAG architectures, vector databases, and state/memory management.Engineering Fundamentals: Strong understanding of software development best practices, version control (Git/GitHub), and CI/CD pipelines.Execution & Communication: Demonstrated ability to translate high-level business goals into clean, maintainable, and well-tested code.Nice-to-Have:Active contributions to open-source AI projects or personal projects visible on GitHub.Experience optimizing token usage, latency profiling, and LLM cost-attribution models.What We Offer (Contractor)Contractor agreement with payment in USD.100% remote work in an international setting.Access to Argentine public holidays.Direct involvement in building cutting-edge conversational AI products.Access to learning platforms, referral rewards, and English classes.
#J--Ljbffr

📌 Ai Engineer · Senior · Latam (Rosario)
🏢 Darwoft
📍 Rosario