About Seev
- We started by transforming how professional services firms write proposals. Today, Seev is becoming the AI layer for their entire revenue operation
- Bootstrapped to 30+ customers, including market leaders like Telus, Levio, BPA
- We've grown ARR >400% since Jan. 2026
- Rapidly moving up-market with no signs of slowing down
- Customers love how we combine pace of innovation and attention to detail
About This Role
You will join Seev's founding engineering team in a fundamentally full-stack AI engineering role. Most of the work is production backend systems: agent architecture, retrieval pipelines, and document processing.
We are a small, fast-moving team, so requirements are not always fully defined at the outset. You will need to build your own context, spot the gaps, and carry a feature from a rough idea through to something running in production that is used by real customers. We value ownership, clear communication, and hands-on execution over process for its own sake.
Role Requirements
- 5+ years of software engineering experience, including significant production backend work.
- Strong Python, including async programming, Pydantic validation, testing, and API design (FastAPI or similar modern framework).
- Hands-on experience shipping production features with Anthropic, OpenAI, Gemini, or comparable foundation-model APIs.
- Experience building AI agents or multi-step LLM workflows: function calling, structured outputs, conversation state, context management.
- Experience with document-grounded generation, including embeddings, vector/lexical search, and context assembly.
- Working knowledge of AWS event-driven systems (Lambda, SQS, EventBridge, S3) and MongoDB or another document database.
- Comfortable using AI-native dev tools (Cursor, Claude Code) to move fast without cutting corners on quality.
You Could Be a Great Fit If
- You would rather own a feature end-to-end than hand off a spec and wait for someone else to build it.
- You can take a vague, half-formed product idea and turn it into a shipped, working system.
- You have debugged production LLM failures using logs, traces, and reproducible test cases.
- You know when to write the test, add the eval, or improve the abstraction, and when those are a waste of time.
- You communicate technical trade-offs clearly to non-technical teammates without dumbing them down.
- You are comfortable being one of a handful of engineers, with no safety net of a large team behind you.
Bonus
- Experience with Beanie ODM or MongoDB Atlas vector search.
- Experience with document parsing, OCR, or programmatic DOCX/PDF/XLSX editing.
- Familiarity with React and TypeScript.
- Experience with Terraform, GitLab CI/CD, or production-monitoring tools.
- Experience in RFPs, proposals, procurement, or other document-heavy B2B functions.
Who Should Not Apply
- You want fully-specced tickets and a defined, repeatable process handed to you.
- You need a large team, a deep bench, and an established platform before you can be productive.
- You see AI-assisted coding tools as something to get around to rather than something you already rely on.
- You would rather do research than ship production code that customers depend on.
- You are uncomfortable with ambiguity, or with being wrong sometimes as you figure things out in real time.
Our Philosophy
- We believe small teams of very talented people, given real ownership, outperform large teams with more process. We hire and compensate accordingly.
- We value people who can seek answers independently and loop in the founders when they actually need to.
- We would rather ship something real and improve it in production than perfect it in the abstract.
- We value principled thinking and a strong sense of ownership over years of experience alone.
Benefits
- Compensation includes salary + equity
- Three weeks of PTO per year
- Flexible work schedule
- Remote-first
