Senior Full Stack Engineer

Xplor Technologies powers the experiences at the heart of everyday life. Through modern vertical software, embedded payments, and AI-powered capabilities, we help businesses in fitness, recreation, golf and club, field services, laundry, education, and other membership-based and service-based industries simplify operations, uncover insights, and elevate customer and member experiences.

About the opportunity

AI Engineering builds the shared platform that powers AI across every Xplor product: the agent runtime, model gateway, retrieval, guardrails, evaluations and cost controls. We solve the hard problems once, so product teams can ship AI features quickly and safely.

We’re looking for a hands-on Senior Full Stack Engineer who enjoys turning what AI agents can do into software people rely on every day. You’ll work across the whole stack, from agent runtime and APIs to retrieval and the interfaces people use to work with agents. You’ll partner with product teams to get their agents into production, shape technical direction, mentor others and raise the bar for how we build with AI.

Why this role is exciting

- Build the platform, not just a feature. Your work powers AI across a portfolio of products used by more than 130,000 businesses.
- Real agents in production, not demos. Orchestrator agents that hand work to specialist agents, long-running background tasks, and human approval before real-world actions.
- A full retrieval engine. Hybrid vector and keyword search, reranking, and vision models that read PDFs and charts.
- Hard problems at scale. Tenant isolation across thousands of businesses, streaming responses, and making every task faster and cheaper.
- AI-native engineering. We build AI with AI. Coding agents and spec-driven development are part of everyone’s daily workflow.

This position has an annual base salary range of $180,000 to $200,000 USD.

This is a fully remote role open to candidates based anywhere in the U.S., excluding Hawaii and Alaska. We’d prefer candidates in the Eastern or Central time zones.

At Xplor, we believe that the best innovation and ideas happen at the intersection of differences - people of different cultures, generations, disciplines, and lived experiences. So even if you think you don’t quite tick all the boxes, we still encourage you to apply.

Responsibilities

Build reliable agent workflows that combine models, retrieval, tools and human approval, including multi-agent handoffs, long-running tasks and state that persists across steps.; Improve how documents and business data are ingested and retrieved, and measure answer quality with automated offline and online evaluations.; Keep customer data safe through tenant isolation, permissions, prompt-injection defences, careful handling of personal data and audit trails.; Build reusable UI components, SDKs and integrations (including MCP) that product teams can embed in their own apps.; Design agent interfaces people trust, with streaming responses, clear agent status, human approval steps and accessibility built in.; Track cost, latency and quality, trace agent runs end to end, and make agents faster and cheaper.; Work with product teams to turn early ideas into shipped features.; Lead technical design for major platform features, write clear design docs and set high standards through code review.; Mentor engineers across AI Engineering and product teams, and help shape how Xplor builds with AI.; Share on-call for the services you build, supported by our Site Reliability Engineers.

Requirements

6+ years building and shipping production software, with recent experience at a senior level.; Strong Python backend experience, ideally with FastAPI, Pydantic and async services.; Solid TypeScript and React skills, and experience building reusable components or SDKs other teams use.; Hands-on experience building with LLMs in production, such as tool calling, retrieval-augmented generation (RAG) or agent workflows, and an understanding of how they fail differently from traditional software.; Experience with retrieval and search, such as vector databases (pgvector or similar), hybrid search, chunking or reranking.; Good working knowledge of PostgreSQL and data modelling, including performance and migrations.; Experience building multi-tenant SaaS, with a strong sense of data security, permissions and handling personal information.; Comfort running what you build on AWS, using infrastructure as code (Terraform or similar), CI/CD and monitoring tools such as Datadog.; A habit of measuring things: evaluating AI output quality, tracking cost and latency, and using data to make improvements.; Experience leading technical design, writing clear design docs and mentoring other engineers.; You use AI coding tools every day, with good judgement about where human review still matters.

Nice to have

Built multi-agent systems, long-running background jobs or human-in-the-loop approval flows.; Worked with MCP, LiteLLM or Amazon Bedrock.; Built automated evaluations for LLM or RAG systems (offline and online).; Experience with prompt-injection defences or AI security.; Built streaming user interfaces (server-sent events) or accessible, trustworthy AI interfaces.; Worked in regulated environments such as SOC 2 or PCI DSS.

Benefits

Paid Parental Leave benefit programs; #GiveBackDays/Commitment to social impact – 3 extra days off to volunteer and give back to your local community; Ongoing dedication to Diversity & Inclusion initiatives such as D&I Council, Global Mentorship Program; Access to free mental health support; Flexible working arrangements