Lead Engineer - Agentic AI Systems (United States)

About the Company Nuaav is a boutique consulting firm that positions itself as a strategic partner for corporate leaders, focusing on delivering real business results and driving impactful change in complex and rapidly evolving business environments. Unlike large-scale consulting firms, Nuaav brings the boutique advantage — specialized expertise, personalized attention, agility, and tailored solutions — ensuring higher service quality and true alignment with client needs. Our core service areas include: Product Engineering — end-to-end product lifecycle development with emphasis on innovation, reliability, scalable DevOps practices, and integration of emerging technologies such as AI, IoT and Blockchain. Data Systems — enterprise-scale data architecture, integration, governance, real-time processing, and big data solutions. AI and Machine Learning — predictive analytics, automation, and intelligence solutions to optimize strategy, performance and customer engagement. User Experience — intuitive, research-driven design solutions to enhance customer experience and retention. About the Role We are looking for a Lead Engineer — Multi-Agentic AI Systems with 7+ years of experience designing and shipping intelligent, production-grade platforms powered by agentic AI. This role owns the full lifecycle of AI-driven backend systems — from architecture through deployment — where multiple autonomous agents coordinate across LLMs, tools, data sources, and external services. You will define how agents are orchestrated, evaluated, and governed, ensuring every workflow is reliable, safe, and observable in production. Key Responsibilities Architect and build multi-agentic systems encompassing agent orchestration, tool routing, shared memory, planning loops, and inter-agent communication patterns. Design and maintain an AI Gateway layer that manages model routing, rate limiting, request transformation, fallback strategies, and unified observability across LLM providers. Establish evaluation (evals) frameworks to systematically measure agent accuracy, latency, cost efficiency, and task-completion quality across diverse workflows. Define and enforce guardrails — including input/output validation, content filtering, hallucination detection, policy compliance, and human-in-the-loop escalation — to ensure safe, predictable agent behavior. Evaluate, integrate, and extend agentic frameworks such as LangGraph, Google ADK, CrewAI, Microsoft Agent Framework, or similar tooling, selecting the right abstractions for each use case. Design scalable backend services in Python with a cloud-native mindset (AWS preferred), emphasizing reliability, horizontal scalability, and fault tolerance. Lead integration of LLMs with enterprise data platforms such as Snowflake or Databricks, defining semantic layers and data models optimized for agent consumption. Translate ambiguous product requirements into structured technical solutions and guide team members on leveraging AI-assisted development tools. Own system performance, reliability, incident response, and continuous improvement across the agentic platform. Required Skills