Lead Engineer - AI Platform
Ireland • Full-time
Posted 4d ago
Job Location
Ireland
Also open in Germany, Spain, Switzerland, UK, Netherlands, France
Tech Stack
Remote Work Policy
On-site
Employment Type
Full-time
Categories
AI Infrastructure Engineer
About the job
Accountabilities:
As Lead Engineer - AI Platform, you will take ownership of the technical foundations that enable AI agents to operate reliably at scale, while providing engineering direction and developing a high-performing team. Your key responsibilities will include:
Design and develop agent execution systems capable of managing long-running, multi-step AI tasks, including orchestration, tool calling, multiple model providers, and execution safeguards.
Build and maintain scalable distributed worker systems on cloud infrastructure, ensuring customer isolation, fault tolerance, and safe deployment processes.
Define how conversations, workflows, files, and other application data are stored and maintained consistently under concurrent usage.
Develop real-time experiences that stream task progress and results to users while AI processes are running.
Implement accurate usage metering, cost tracking, tracing, and observability systems to monitor performance and resource consumption.
Establish technical direction through architecture decisions, design documentation, code reviews, and engineering standards for reliability and testing.
Lead, mentor, and manage a small engineering team, overseeing planning, performance reviews, on-call responsibilities, and recruitment as the team expands.
Define and improve AI-driven engineering practices using tools such as Claude Code, Codex, and Cursor, including effective context management, instructions, testing frameworks, and human review processes.
Drive continuous improvements in platform reliability, execution speed, cost accuracy, and scalability.
Use performance metrics, logs, and traces to investigate technical issues, identify root causes, and implement effective solutions.
Requirements:
The ideal candidate combines deep backend engineering expertise with hands-on experience building production-grade AI systems and leading engineering teams. You should be comfortable working with distributed architectures, LLM integrations, and modern AI-assisted development workflows, while maintaining a strong focus on performance, reliability, and measurable outcomes. The following qualifications are expected:
At least 7 years of experience building and maintaining backend systems in production environments.
Strong proficiency in Python as a primary programming language; experience with Go is an advantage.
Proven experience designing and operating distributed workers or job-processing systems using Kubernetes or similar technologies, including queues, autoscaling, and safe deployments.
Strong knowledge of relational databases, caching systems, concurrency, and performance optimization under load.
Hands-on experience building production applications with LLM APIs, including tool usage, streaming, token budgets, provider errors, and rate-limit management.
Familiarity with AI agent frameworks and multi-agent architectures is an advantage.
Extensive practical experience using AI coding agents in everyday engineering workflows, with the ability to provide appropriate context, structure tasks, validate generated code, and identify potential risks.
Demonstrated experience leading small engineering teams, setting technical direction, mentoring engineers, managing performance, and overseeing delivery.
Strong debugging and analytical skills, with the ability to use logs, traces, and metrics to identify and explain root causes before implementing fixes.
Strong attention to engineering quality, including testing, reliability, failure handling, and maintainability.
Ability to balance technical leadership with hands-on development and execution.
Benefits:
25 days of paid time off, in addition to public holidays, with a Flexible Time Off scheme.
Health insurance or private medical coverage.
Monthly stipend for wellness, fitness, and learning and development.
Fully remote working arrangement, with the flexibility to work from anywhere within your home country.
Enhanced parental leave policies covering birth, adoption, and surrogacy.
Flexible working hours.
Access to office facilities in The Shard, London, for eligible UK-based employees.
Opportunity to work on innovative generative AI products and advanced multi-agent architectures.
Opportunity to influence technical strategy and lead the development of a growing AI engineering platform.
