LLM Application Engineer

About ActAI

ActAI aims to transform everyday applications like email, notes, tasks, and calendars—currently used by over 5 billion people—by embedding proactive intelligence. The goal is to create AI-native experiences that minimize or eliminate the need for complicated user prompts, focusing on enhancing conversations, scheduling, and workflow management. The product emphasizes high reliability in supporting extended workflows, persistent context retention, and effective task completion, while significantly reducing AI hallucinations. Ultimately, ActAI seeks to help organize users' lives to enable them to concentrate on meaningful activities.

Role Overview

The LLM Application Engineer will develop the intelligence backbone supporting ActAI's AI user experiences. This role operates where large language models, software engineering, and product design converge—crafting agent workflows, refining model performance, and transforming AI functionalities into dependable user interactions. The engineer will manage end-to-end problem solving, from capturing user requirements to designing agentic workflows, integrating models and services, building evaluation systems, and perpetually enhancing AI behavior in production.

Key Responsibilities

• Develop and deploy applications powered by large language models (LLMs) and agent workflows.
• Design architectures for reasoning, planning, memory management, tool usage, and execution of multi-step processes.
• Create robust orchestration pipelines that convert uncertain model outputs into consistent, trackable, and safe actions.
• Integrate LLMs seamlessly with APIs, databases, search engines, internal services, and third-party tools.
• Implement best practices in prompting, context engineering, structured outputs, and tool invocation to enhance model behavior.
• Construct evaluation frameworks and datasets for assessing AI quality, reliability, and detecting regressions.
• Troubleshoot AI systems across all layers—from model outputs and prompts to orchestration, backend services, and UI/UX.
• Optimize AI system performance regarding quality, latency, and operational cost.
• Collaborate closely with product and engineering teams to convert vague product challenges into actionable AI solutions.
• Establish robust production standards for observability, tracing, experimentation, evaluation, and continuous refinement.

Technology Stack

• Python programming
• APIs for LLMs including OpenAI-compatible and open-weight models
• Agent frameworks and orchestration platforms
• Vector databases and retrieval mechanisms
• Backend services and distributed systems architecture
• Machine learning frameworks such as PyTorch and JAX

Preferred Candidate Profile

• Solid foundation in software engineering, ideally with experience developing AI-powered applications.
• Practical experience with large language models, generative AI technologies, or agent-centric systems.
• Skilled in designing prompts, AI workflows, evaluation methods, and refining AI behavior.
• Capable of delivering clean, maintainable production code.
• Comfortable navigating across abstraction layers from AI models to systems and products.
• Strong analytical and problem-solving abilities in dynamic, fast-paced environments.
• Proactive inclination towards shipping early, iterative development, and continuous improvements.

Expected Impact

• Accelerate bringing AI features to production that yield quantifiable benefits for users.
• Develop LLM-based workflows which are scalable, dependable, transparent, and maintainable.
• Enhance AI quality through systematic evaluation, experimentation, and repeated iterations.
• Improve predictability, efficiency, and cost-effectiveness of AI workflows over time.
• Simplify complex AI capabilities into intuitive, user-friendly experiences.