Role overview
They are seeking an experienced AI Agent Engineer who specializes in large language models (LLMs), agent architectures, and tool-enabled AI systems. You will design, implement, and deploy multi-step agent pipelines, build robust ML pipelines for model training and fine-tuning, and manage inference infrastructure. This role blends ML research, systems engineering, and product-oriented delivery.
*Key Responsibilities
Agent Development & Integration (≈60%)**
- Design and implement complex, multi-step agent pipelines using both open- and closed-source LLMs.
- Build tools and adapters that allow agents to interact securely with enterprise applications and APIs.
- Ensure agent behavior aligns with business objectives, reliability targets, and relevant compliance requirements.
What we're looking for
- Experience deploying production-grade, large-scale AI applications with attention to reliability and cost.
- Familiarity with model evaluation, observability, A/B testing, and post-deployment monitoring for AI.
- Strong communication skills for translating technical tradeoffs to non-technical stakeholders.
- The opportunity to build systems that materially improve how businesses operate using AI.
- High ownership and a direct influence on product and architecture decisions.
- A collaborative engineering culture focused on impact, quality, and rapid iteration.