About the role
Requirements:
- 5-8 years of software engineering experience, including meaningful experience building and shipping AI-powered products in production.
- Strong CS fundamentals and engineering discipline; this is a builder role, not a research role.
- Can clearly explain difficult AI systems they've built, what failed, what they learned, and how they improved reliability over time.
- Deep understanding of LLM application architecture, including tool use, structured outputs, retrieval, orchestration, and production failure modes.
- Experience building agentic systems that perform multi-step reasoning and interact with tools or business systems.
- Prompt lifecycle management: treats prompts as versioned, testable, deployable artefacts, not strings scattered through the codebase.
- Strong RAG fundamentals: retrieval quality, chunking strategies, embeddings, evaluation, and knowledge system design.
- Experience designing evaluation frameworks and regression testing pipelines for AI systems.
- Strong understanding of observability for AI applications: tracing, monitoring, feedback loops, and production debugging.
- Experience balancing capability, latency, reliability, and cost when designing AI systems.
- Solid grasp of responsible AI, enterprise security, privacy, and governance considerations.
- Product-quality frontend skills and the ability to own AI experiences end-to-end.
- Strong backend engineering skills and the ability to build production-ready systems independently.
Good to have:
- Memory architectures: episodic memory, procedural memory, retrieval systems, and knowledge stores.
- Agent orchestration frameworks such as LangGraph, Pydantic AI, OpenAI Agents SDK, CrewAI, or custom runtimes.
- Experience building long-running autonomous workflows and event-driven agent systems; voice, multimodal, and real-time AI systems.
- Fine-tuning experience and understanding of model internals beyond API consumption.
- Open-source model deployment and inference infrastructure.
- Experience building AI systems for enterprise workflows where correctness, auditability, and trust are critical.
- Experience with evaluation platforms, benchmark design, and AI quality measurement.
- Familiarity with financial systems, billing platforms, revenue operations, accounting, or fintech domains.
- Experience with MCP, tool ecosystems, and AI platform architectures.
- Startup experience and comfort operating in high-ownership environments.
- Not taking yourself too seriously.