Summary
✨ AI‑Generated
Build the intelligence layer behind next-generation AI applications. You will design agent workflows, improve LLM behavior, and translate advanced AI capabilities into reliable user experiences. The role sits at the intersection of software engineering, AI, and product development, with substantial end-to-end ownership.
Highlights
Build AI experiences at the intersection of LLMs, software engineering, and product. The role offers end-to-end ownership of challenging problems and the opportunity to improve agent workflows, model behavior, reliability, and user experiences.
Description
About ActAIThere are over 5 billion users using basic applications today such email, notes, tasks, calendar and they're not AI-native.
Our mission is to build proactive applications for anyone in the world, who are not used to complex prompting.
We aim to bring intelligence to conversations, errands, organising and workflows, with minimal to no prompting.
Our product focuses on achieving high reliability for long-running workflows, persistent context, and real-world task completion.
We believe products will greatly reduce hallucinations.
Our objective is to organise anyone's life, allowing us all to spend time on valuable and meaningful things.
About the RoleAs an LLM Application Engineer, you will build the intelligence layer that powers ActAI's AI experiences.
You will work at the intersection of LLMs, software engineering, and product - designing agent workflows, improving model behaviour, and turning AI capabilities into reliable user experiences.
You will own problems end-to-end, from understanding user needs, designing Agentic workflows, integrating models and tools, building evaluation system and continuously improving AI behaviour in production.
FocusBuild and ship LLM-powered applications and AI agent workflowsDesign systems for reasoning, planning, memory, tool uuse and multi-step executionBuild reliable orchestration pipelines that turn probabilistic model outputs into predictable, observable, and safe actionsIntegrate LLMs with APIs, databases, search, internal services, and external tools.Develop prompting, context engineering, structured outputs, tool-calling, and other techniques to improve model behaviourBuild evaluation frameworks and datasets to measure AI quality, reliability, and regressionsDebug AI systems across the entire stack—from model behaviour and prompts to orchestration, backend services, and product UXOptimise AI systems for quality, latency, and costWork closely with product and engineering teams to turn ambiguous product problems into working AI solutionsEstablish production practices for observability, tracing, experimentation, evaluation, and continuous improvement
Tech StackPythonLLM APIs and model providers, including OpenAI-compatible APIs and open-weight modelsAgent frameworks and orchestration systemsVector databases and retrieval systemsBackend services, APIs, and distributed systemsPyTorch / JAX
Ideal ExperienceStrong software engineering fundamentals with experience building AI-powered applicationsHands-on experience with LLMs, generative AI, or agent-based systemsExperience designing prompts, workflows, evaluations, or AI behaviourAbility to write clean, production-quality codeComfortable working across abstraction layers (model → system → product)Strong problem-solving skills in ambiguous, fast-moving environmentsBias toward shipping, iteration, and continuous improvement
OutcomesAI features reach production quickly and deliver measurable user impactLLM-powered workflows are reliable, scalable, observable, and maintainableAI quality improves through systematic evaluation, experimentation, and iterationAI workflows become increasingly predictable, efficient, and cost-effectiveComplex AI capabilities are translated into simple, intuitive user experiences
