Generative AI Engineer

Role Overview

We are looking for an AI Engineer (3–5 years experience) to join our engineering team within a lean 2-person pod structure. In this role, core engineering fundamentals come first: you will design, deploy, and operate scalable backend services and microservices alongside production agentic workflows. You will own features from architecture discussions to live production monitoring with high independence.

Key Responsibilities

• Backend & API Engineering: Build and maintain scalable backend microservices and APIs using Python, FastAPI, Docker, and AWS EKS / Kubernetes.
• Agentic Workflows: Implement end-to-end agentic logic, including agent loops, state management, and tool orchestration using frameworks such as LangGraph, LangChain, Strands, ADK, or custom frameworks.
• Evaluations & Monitoring: Build ground-truth evaluation datasets, set up automated eval pipelines, and integrate observability tools for tracking live agent performance.
• Lean Pod Execution: Operate autonomously within a lean 2-person pod, taking full accountability for feature execution with minimal guidance.
• Production Support & Debugging: Identify and resolve edge cases in agent execution, API latency bottlenecks, state synchronization issues, and deployment bugs.

Required Qualifications & Experience

• Experience: 3–5 years in core software and backend engineering.
• Agentic Experience: 1–3 years of hands-on experience building and deploying agentic AI applications into live production environments.
• Core Tech Stack: Strong proficiency in Python, FastAPI, REST APIs, Docker containerization, and Kubernetes (EKS).
• Framework Knowledge: Practical experience with at least one agentic framework (LangGraph, LangChain, Strands, ADK, or equivalent custom framework with clear engineering trade-off rationale).
• Production Engineering: Proven track record of personally deploying and maintaining production systems—not merely theoretical or conceptual knowledge.