About Our Client

Servant is partnering with a forward-thinking organization focused on helping teams work smarter, not harder. By combining thoughtful strategy, intuitive tools, and a people-first mindset, enabling organizations to optimize how work gets done—improving efficiency, clarity, and outcomes across the business.

With a strong emphasis on collaboration and continuous improvement, our client partners closely with its customers to solve real-world challenges and deliver practical, scalable solutions. The team values curiosity, ownership, and impact, and is committed to building products and experiences that genuinely support the way people work today.

As our client continues to grow, they are investing in talented, mission-driven individuals who want to shape the future of work and make a meaningful difference for customers and teammates alike.

Role Summary

Our client is building the world’s first Human-Led AI Orchestration Layer—a platform designed to keep humans firmly in control of AI through clarity, accountability, and execution via our proprietary Action Points.

As an AI Engineer, you will design and implement the intelligence layer that translates raw information into human-directed outcomes. You will work across LLMs, agentic workflows, and AI pipelines to ensure AI remains a tool governed by human intent, not an autonomous system.

Everything you build is expected to be revenue-ready, secure, and production-grade.

Key Responsibilities

AI & Intelligence Engineering

• Design and implement AI-driven workflows that generate actionable, human-directed insights.
• Build and optimize LLM-powered systems for summarization, recommendation, classification, and orchestration.
• Implement agentic AI patterns that operate under explicit human guardrails and approval flows.
• Translate unstructured data into structured Action Points™ aligned with user goals.
• Develop and maintain prompt architectures and evaluation frameworks for consistent AI output quality.
• Architect and develop semi-autonomous AI agents with mandatory human-in-the-loop control points, safety guardrails, and review checkpoints.

Voice to Text

• Design and implement AI-driven voice workflows that generate actionable, human-directed insights.
• Architect real-time speech-to-text pipelines for AI control, command execution, and Action Point generation.
• Implement low-latency voice ingestion using Azure Speech SDK for real-time transcription, intent detection, and multilingual support.
• Ensure voice inputs are securely processed, auditable, and aligned with human authorization and approval flows.
• Translate spoken input into structured, human-directed Action Point that govern downstream AI agents.

Integration & Deployment

• Deploy AI services using FastAPI and integrate them securely with backend systems.
• Collaborate with frontend and backend engineers to expose AI capabilities via secure APIs.
• Ensure AI systems scale reliably in cloud environments (Azure-based).

Performance, Ethics & Governance

• Optimize inference latency, throughput, and cost efficiency.
• Implement observability, logging, and monitoring for AI workflows.
• Apply responsible AI principles: transparency, auditability, and human override by design.