Staff AI Engineer

Felix Technologies, Inc.•Miami, FL

1d•Remote

About The Position

We are seeking a visionary and highly technical Staff AI Engineer to join our EngOps team within the new Enterprise AI squad. This role is central to our next phase of growth, focusing on designing, building, and scaling the core autonomous AI infrastructure that powers both our customer-facing product and internal engineering operations. In this role, you will be the architect behind our "Maestro" (our central AI orchestrator) and its distributed execution systems. You will be instrumental in evolving our WhatsApp-based AI platform into a sophisticated, multi-agent enterprise system capable of reasoning, planning, and automating complex, multi-step tasks across critical internal and product functions (e.g., loans, payments, fraud). You will act as a foundational technical anchor for EngOps, helping shape the future architecture of this new squad and analyzing what the division needs next as we scale. If you thrive at the intersection of deep software infrastructure, operational excellence, and agentic AI, this is your mission.

Requirements

8+ years of hands-on experience in software engineering, with a strong, proven background in infrastructure and systems development, and at least 2 years dedicated to building and deploying production-grade AI applications focused on LLMs.
Exceptional expertise in Python and deep knowledge of System Architecture. Mastery of core LLM APIs and agentic frameworks.
Proven experience implementing complex agentic systems, including RAG, tool-calling, vector databases, and advanced memory/state management.
High ownership and comfort working in an early-stage squad environment—someone who can independently analyze operational bottlenecks, propose architectural solutions, and code them.
Equivalent competencies in any of the above will also be considered.

Nice To Haves

Hands-on experience or active experimentation with Open CLAW, Hermes, or advanced open-source AI Agent frameworks.

Responsibilities

Architect, develop, and maintain the core infrastructure for our central AI orchestrator ("Maestro") and its connected execution agents to optimize engineering and enterprise operations.
Lead the integration of AI agents into core product and operational infrastructure. Own the full lifecycle from containerization (Docker/Kubernetes) to CI/CD deployment, ensuring high availability, security, and post-launch stability.
Establish production-grade monitoring, tracing, and logging for complex agentic workflows within the EngOps ecosystem to track reasoning paths, tool-calling success rates, and latency bottlenecks.
Design automated "evals-as-code" using LLM-as-a-judge, semantic similarity testing, and adversarial benchmarking to ensure agent safety, reliability, and groundedness.
Optimize RAG pipelines and agent loops for production constraints, implementing caching strategies, prompt compression, and model routing to balance inference costs with high performance.
Define operational best practices for AI deployment, asynchronous programming, and structured data validation. Help map out future team and infrastructure needs.