EggAI · Full-time · Remote (EU only)

The Role

A very strong senior software engineer with deep, hands-on experience building and operating production systems. We hire for engineering strength first: people who write good software, reason about failure, and own what they ship.

You will work in a team of 2 to 6 engineers on a client project. Clients come to us because we work at the forefront of AI in the enterprise; you help implement our AI strategy.

AI experience is not required. Much of our work involves LLM-powered and agentic systems, but we would rather hire an excellent engineer and let them learn that domain.

What You'll Do

• Build and operate the production systems at the centre of the engagement, end to end — you own what you ship, including after it's reached production
• Lead architecture discussions for your part of the system, with the support of the wider team
• Take ownership: pick up the ambiguous problem, chase down the answer, and say so when something is going wrong
• Work directly with the client's engineers and with our project manager / product owner
• Work in a "normal" team rhythm — daily standups, planning, retrospectives, code and design review

What We're Looking For

• 5+ years designing, building and maintaining production systems that real users depend on — clean testable code, sound API and data modelling, and the judgement to know which abstractions are worth it
• Has owned code in production — deployment, monitoring, on-call or equivalent — and can debug hard problems in live systems: concurrency, performance, data correctness
• Distributed systems fundamentals: services, queues, retries, idempotency, failure modes, and integrating third-party APIs that are not reliable
• Databases: schema design, query performance, migrations
• Operational rigour: meaningful automated testing, useful instrumentation, CI/CD and shipping incrementally
• Client-facing ability: has delivered against real business requirements and can hold a technical conversation with non-engineers
• Languages: Python (primary), TypeScript/JavaScript. Strong engineers coming from Go, Java, C#, Rust or similar who are willing to work in Python are in scope
• Infrastructure: cloud platforms (AWS/GCP/Azure), containerisation

Desired qualities

• Depth — can explain the systems they built and the trade-offs they chose
• Balances speed of iteration with production reliability
• Clear communicator, in writing as well as in conversation
• Learns new domains quickly and deliberately

Nice to have — applied LLM experience

Not required, but worth probing where it exists:

• Building production-grade LLM-powered applications, including multi-agent or tool-calling pipelines
• Handling the real-world problems: latency, cost, reliability, prompt injection, hallucination
• Evaluation and observability for LLM pipelines (eval suites, tracing, prompt versioning)

Interview Process

1. Introductory call - 20-30 minutes
2. Technical interview (choice of walking through own code, live coding, or take home exercise) - 60 minutes
3. Behavioural/Management interview - 60 minutes