Senior AI Engineer (Agentic Systems / LLMs / Python) · LATAM

Location: Anywhere in LATAM
Job Type: Remote
Project: Fintech Conversational AI Platform
Time Zone: Flexible within LATAM
English Level: B2 / C1

Important Notice: Commitment & Focus

This is a full-time role that requires clear dedication and priority to Darwoft projects during the established working hours.

The position is not compatible with other full-time professional engagements. Any additional professional activity must be disclosed in advance and must not interfere with the responsibilities, availability, or working hours required for this role.

Get to Know Us

At Darwoft, we create software that drives real change. But we're more than just tech — we're people first.

We believe in building human-centered digital experiences while working with curiosity, collaboration, and purpose. Based in Latin America, we partner with companies worldwide to develop innovative solutions that combine strong engineering, product thinking, and real business impact.

We work remotely, collaboratively, and with a strong sense of community — always embracing continuous learning, adaptability, and meaningful impact.

About the Role

We're looking for a Senior AI Engineer to join a high-impact fintech project focused on building next-generation conversational AI systems.

This is not a traditional chatbot role.

You'll work on production-grade agentic systems, helping evolve AI from simple user interactions into autonomous, multi-agent architectures capable of reasoning, planning, and executing complex workflows across critical business domains.

In this role, you'll be close to the core AI strategy, collaborating with product, engineering, and business teams to bring intelligent systems into real-world production environments — with direct impact on thousands of users.

This is a strong opportunity for someone who combines solid software engineering foundations, hands-on experience with LLMs and agentic architectures, and the ability to turn business problems into scalable AI-powered solutions.

What You'll Be Doing

• Design, build, and deploy stateful AI agents using Python and modern agentic frameworks such as LangGraph, CrewAI, or similar tools.
• Develop multi-agent systems capable of handling complex, multi-step workflows involving reasoning, planning, memory, and tool usage.
• Implement and optimize RAG pipelines using vector databases to deliver accurate, contextual, and grounded outputs.
• Integrate AI agents into core product infrastructure, including APIs, internal services, workflows, and business-critical systems.
• Build LLMOps capabilities, including monitoring, tracing, evaluation, and observability of agent behavior, latency, tool usage, and reasoning paths.
• Design and maintain advanced evaluation pipelines using techniques such as evals-as-code, LLM-as-a-judge, semantic similarity, and adversarial testing.
• Optimize AI systems for performance, reliability, and cost efficiency through prompt optimization, caching, model routing, and architecture decisions.
• Ensure production readiness through CI/CD pipelines, containerization, testing, and reliability practices.
• Collaborate with cross-functional teams to translate business needs into scalable AI solutions.
• Contribute to engineering best practices, technical decision-making, and AI system design standards.

What You Bring

• 7+ years of experience in software engineering.
• 2+ years of hands-on experience building AI, Generative AI, or LLM-based systems in production.
• Strong proficiency in Python.
• Experience working with LLM frameworks and APIs such as OpenAI, LangChain, LlamaIndex, LangGraph, CrewAI, or similar.
• Proven experience designing agentic systems, including multi-agent workflows, memory/state management, tool usage, and orchestration.
• Solid understanding of RAG architectures, embeddings, retrieval strategies, and vector databases.
• Strong software engineering fundamentals, including Git, testing, CI/CD, APIs, and clean architecture principles.
• Experience integrating AI systems into real production environments, beyond prototypes or proof-of-concepts.
• Ability to translate complex business problems into scalable technical solutions.
• Strong communication skills in a remote, English-speaking environment.

Nice to Have

• Experience in fintech, payments, fraud prevention, risk, banking, or financial platforms.
• Experience with LLMOps and observability tools such as LangSmith, Arize, Weights & Biases, or similar.
• Experience with evaluation frameworks and benchmarking for LLM systems.
• Background optimizing AI systems at scale, especially around latency, cost, accuracy, and reliability.
• Experience with Docker, Kubernetes, cloud infrastructure, or distributed systems.
• Contributions to open-source AI projects, technical communities, or public AI experiments.
• Experience working in high-growth, fast-paced product environments.

What Darwoft Offers

• Contractor agreement with payment in USD.
• 100% remote work.
• Argentina's public holidays.
• English classes.
• Referral program.
• Access to learning platforms.

Explore this and other opportunities at:
www.darwoft.com/careers