Staff Software Engineer - AI Platform

Staff Software Engineer – AI Platform

Location: Brooklyn, Frisco, Eagan, Toronto, or Ann ArborLevel: Staff / Lead Software EngineerWe’re working with a leading technology company building AI-native products that are changing how professionals work with complex, document-heavy information.We’re looking for a hands-on Staff Software Engineer to help shape the backend and AI platform powering these products.

This is a high-ownership role for an engineer who enjoys being close to the code while also setting technical direction across a team.The roleYou’ll work on the systems behind production AI agents, conversations, knowledge bases and complex workflows. You’ll help define how AI capabilities are built, integrated and operated reliably at scale.You’ll have the opportunity to:Lead large, multi-quarter technical initiatives across AI, product and infrastructureDesign and build backend services and distributed systems using Python, FastAPI, PostgreSQL and AWSBuild AI orchestration involving LLMs, agents, tool calling, MCP and multi-step workflowsDevelop retrieval, search, vector and document-processing capabilitiesDesign for high-throughput, low-latency AI workloads, including caching, queuing, rate limiting and model failoverEstablish strong approaches to observability, testing, reliability and incident responseMentor engineers and influence technical direction across the wider organisationWork closely with product, ML and research teams to turn emerging AI capabilities into reliable production systemsYou’ll ideally have:5–7+ years of software engineering experience building scalable cloud applications and APIsStrong, recent hands-on Python experience, ideally with FastAPI or similar frameworksStrong knowledge of distributed systems, backend architecture, APIs, databases and cloud infrastructureProduction experience with AWS and relational databases such as PostgreSQLA track record of owning complex engineering projects from architecture through to productionExperience building or integrating AI/LLM-powered products or platformsExposure to agents, tool calling, MCP, RAG, retrieval, embeddings or vector searchStrong understanding of production reliability, observability, testing and performanceThe ability to influence technical direction while remaining highly hands-onExperience in environments where correctness, auditability or compliance matter is useful, but not essential.Why join?This is a chance to join a small, highly experienced engineering team with a significant technical surface area and the backing of an established global technology organisation.You’ll have genuine ownership over how AI systems are architected and built, with the opportunity to influence engineering practices beyond a single product or feature.If you're a Staff-level engineer who enjoys building AI systems from the ground up — and still wants to be deep in the code — we'd be interested in speaking with you.