Senior/Staff AI-First Product Engineer

About TaxDome

At TaxDome, we’re building the #1 practice management platform for accounting firms in the US and globally. Founded in 2017, we’ve grown into a 400+ fully remote team across 40+ countries, serving tens of thousands of businesses worldwide with millions of end clients.

How we work

You’ll be part of a globally distributed team built on trust, ownership, and self-management.

We focus on outcomes over activity — prioritizing clear ownership, pragmatic decision-making, and accountability for results over rigid processes. Collaboration is central to how we operate: we communicate openly, involve the right people early, and continuously improve how we build products and teams together.

About this role

TaxDome is pivoting from a traditional SaaS to an AI-first engineering organization. We aren't just adding AI features, we are rebuilding our DNA to prioritize agentic workflows, LLM-orchestration, and automated intelligence at the core of our tech stack.

We’re looking for a staff level AI-first Product Engineer to take an absolute, end-to-end ownership of your autonomous domain. You aren’t just a senior coder, you are the technical and operational driver of your domain – you build, own the roadmap, and orchestrate the entire development lifecycle for your specific domain using an AI-first approach to ensure accelerated delivery of value.

What you’ll be responsible for

End-to-End Domain Orchestration

• Absolute Domain Ownership: You design, build, and ship production-grade AI features — from RAG pipelines to multi-step agentic workflows. You own the entire lifecycle, managing your own stability and execution without hand-offs or bottlenecks.

• Rapid Delivery: Pivot from experiment to production in days. Eliminate "documentation taxes" by leveraging AI to generate technical specs and test instantly.

AI-Agentic Development

• Daily Orchestration: Use AI tools (ChatGPT, Claude, Cursor, etc.) to generate and refine code, create tests and technical specs, debug complex issues, refactor legacy systems.

• Harness Engineering: You will design and implement robust agent harnesses to manage the lifecycle of your autonomous agents.

• Validation and Integrity: Act as a quality gate, validate AI outputs, prevent "AI slop", ensure production-grade systems.

Product and Operational Leadership

• Operate as an Architect: You scope ambiguous problems, align stakeholders, and unblock things without being asked. You autonomously design patterns and coding standards for integrating LLMs — prompt management, output validation, context budgeting, and cost control.

• Stay at the Frontier: Evaluate and adopt emerging frameworks (LangGraph, CrewAI, custom) with a critical eye toward production reliability, not hype.

• Balance velocity with rigour: You are comfortable shipping imperfect v1s and systematically improving them.

What you bring

General profile

• Product owner mindset — you can take ambiguous requirements for your domain and turn them into a clear, prioritized roadmap without needing middle-management alignment.

• Startup and Builder DNA — you have a track record of shipping your own projects and working in high-accountability environments.

• Strong full-stack expertise across modern web ecosystems, Python /Node / Go / Ruby

• Fluent in Prompt engineering and LLM API integration

• Deep experience with RAG pipelines: chunking strategies, embedding models, vector DBs (Pinecone, Weaviate, pgvector)

• Shipped production-grade agentic systems using tool/function calling, orchestration, and multi-agent coordination

• Hands-on with guardrails, output validation, and safety patterns for LLM-generated content

• Proven track record in Latency and cost optimization for token-heavy workloads at scale

• Strong English communication skills

Modern AI tools (daily use expected)

• Cursor, GitHub Copilot, or equivalent AI coding assistants

• Claude, GPT-4, and open-weight models (Llama, Mistral) — you know when to use which

• LangChain / LlamaIndex for orchestration, with the judgment to go custom when needed

• Weights & Biases, LangSmith, or equivalent for experiment tracking and eval pipelines

Strong differentiators

• Experience designing LLM evaluation frameworks: benchmarks, regression suites, human eval pipelines

• Familiarity with fine-tuning workflows and RLHF data preparation

• Streaming and async patterns for real-time AI UX (SSE, WebSockets)

• Cloud deployment (AWS / GCP) with containerised AI services

What we offer

At TaxDome, we aim to create an environment where people can do their best work and grow alongside the company.

• Competitive compensation, paid in USD

• Fully remote work with flexible hours

• 30 paid days off annually, plus sick days as needed

• Health & well-being support

• Learning & development budget to support your professional growth

• English lessons reimbursement

• Co-working space reimbursement

• Company-provided equipment (conditions may vary depending on the role)

• A high level of autonomy and ownership in your work

• The opportunity to make a real impact in a fast-growing global SaaS company

• A collaborative, international team with a strong product mindset

If you’re excited about this opportunity and believe you could make an impact at TaxDome, we’d love to hear from you.

Please note, due to the high volume of applications, we are only able to contact shortlisted candidates. We appreciate your interest in the role!