About Us
Atria is an AI-powered ad creative workflow platform designed to help marketing teams generate more revenue by producing winning ads more efficiently. Trusted by top brands like Ryze Superfoods, Solawave, and Loop Earplugs, as well as forward-thinking agencies such as Power Digital, Inspire Digital, and Disruptive Digital, Atria focuses on enhancing performance across Meta and TikTok channels.
Position Overview
We are seeking a highly skilled AI Agent Engineer to join our rapidly growing remote team. This pivotal role involves architecting, developing, and deploying production-grade AI agent systems that power our creative workflow platform. As a core member of our engineering team, you will collaborate closely with cross-functional teams to deliver high-quality, reliable AI solutions that drive our platform's success and maintain our competitive edge.
Key Responsibilities
Architect, develop, and deploy robust, multi-step agentic workflows and multi-agent orchestration systems with a focus on production reliability and governance.
Design and implement memory and context management strategies (e.g., long-term
memory, Human-in-the-Loop (HITL) feedback) to ensure agent coherence and continuous improvement.
Establish and maintain AgentOps (Agent Operations) practices, including evaluation
frameworks, observability, and monitoring for agent performance, cost, and latency.
Implement advanced LLM interaction strategies, including structured prompting, tool
calling, and chain-of-thought (CoT) to maximize model performance and reliability.
Design and implement tool-calling mechanisms to integrate internal APIs for data analysis, image generation, and video generation capabilities into agent workflows.
Collaborate with product and design teams to rapidly prototype, test, and iterate on new agent capabilities based on user feedback.
Ensure the performance, quality, security, and cost-efficiency of all deployed AI agent systems.
Required Qualifications
Technical & Production Skills
Expert-level proficiency in Python and modern backend development, including API design (e.g., FastAPI) and asynchronous programming.
Familiarity with cloud services (AWS or GCP) with a focus on containerization (Docker/Kubernetes) and CI/CD pipelines for agent deployment.
Familiarity with leading agentic frameworks such as LangGraph, PydanticAI, AutoGen, CrewAI, or similar orchestration libraries.
Nuanced understanding of various LLM capabilities, limitations, and their optimal use cases.
Agentic & Data Stack Expertise
Expertise in vector databases (e.g., Pinecone, Weaviate, Qdrant) and embedding models .
Proven experience with Agentic RAG, including advanced retrieval, re-ranking, and source validation strategies.
Experience building and maintaining production-scale data pipelines for knowledge ingestion and agent memory.
Mindset & Collaboration
Bias for action and a builder-first mentality, capable of rapidly prototyping and iterating on complex systems.
Comfortable with ambiguity and continuous experimentation in a fast-paced, remote environment.
Strong problem-solving skills and a proactive approach to identifying and resolving system bottlenecks.
Excellent communication skills for collaborating with technical and non-technical stakeholders.
Preferred Qualifications
Familiarity with marketing fundamentals and ad creative workflows.
Experience with LLM fine-tuning, quantization, and model optimization techniques.
Experience with monitoring and observability tools specific to AI/ML (e.g., LangSmith, Arize, Weights & Biases).
