What you'll build
AI is not a side project here. It is central to our product, our roadmap, and how our customers get value from the platform. We're looking for an engineer who knows how to turn AI capabilities into real product features that ship fast and work reliably at scale.
As an AI Software Engineer, you'll build the AI-powered features that sit at the core of our platform. This is not a research role. You'll take LLMs, embeddings, retrieval systems, and AI agent patterns and turn them into production product experiences that customers interact with every day.
You'll work across the full stack (Python/FastAPI on the backend, React on the frontend) with a focus on integrating AI components into the product in ways that are fast, reliable, and genuinely useful. You'll own features end to end: from designing the right AI approach, to building the backend services, to wiring up the UI, to shipping it and measuring whether it actually works.
We move fast. You'll be expected to ship frequently, iterate based on real usage, and make pragmatic decisions about when to build, when to buy, and when to leverage off-the-shelf models versus fine-tuning. The goal is always impact: features that change how customers use the platform.
Your scope
- Build and ship AI-powered product features end to end, from model integration through API layer through frontend.
- Design and implement LLM-backed workflows: prompt engineering, retrieval-augmented generation (RAG), function calling, agent orchestration.
- Write production Python/FastAPI services that integrate with LLM APIs, vector databases, and proprietary data.
- Build React frontend components that surface AI capabilities to users in intuitive, responsive interfaces.
- Evaluate and select the right AI tools and models for each problem, balancing quality, latency, and cost.
- Instrument AI features with proper observability: logging, evaluation metrics, latency tracking, cost monitoring.
- Iterate quickly based on user feedback and usage data, treating shipped features as starting points rather than finished products.
- Collaborate closely with Product, Data Science, and Design to define what AI-powered experiences should look and feel like.
- Contribute to our integration ecosystem, including MCP (Model Context Protocol) and Agent-to-Agent (A2A) capabilities.
- Write clean, well-tested code and maintain high engineering standards even when moving fast.
What you'll bring
Technical Skills
- Strong proficiency in Python, with hands-on experience building production APIs using FastAPI (or Flask/Django; FastAPI preferred).
- Solid frontend skills in React: you can build UI that surfaces AI features cleanly, not just call APIs from a notebook.
- Real-world experience building product features powered by LLMs, embeddings, or other AI/ML components (not just experimentation or prototyping).
- Familiarity with common AI infrastructure: vector databases (Pinecone, Weaviate, pgvector), LLM APIs (OpenAI, Anthropic, etc.), prompt management, evaluation frameworks.
- Experience with retrieval-augmented generation (RAG), function calling, or agent-based architectures in production settings.
- Comfort with relational databases (PostgreSQL preferred), data modeling, and performance optimization.
- Working knowledge of cloud infrastructure (AWS, GCP, or Azure), CI/CD pipelines, and containerization (Docker, Kubernetes).
- A strong testing mindset: you write tests, you expect tests in PRs, and you know how to evaluate AI output quality beyond vibes.
Mindset & Collaboration
- A bias toward shipping: you'd rather get something in front of users and iterate than polish in isolation.
- Good product instincts: you think about what the user actually needs, not just what's technically interesting.
- The ability to make pragmatic tradeoffs between model quality, latency, cost, and engineering complexity.
- Clear communication with both engineers and non-technical stakeholders.
- Comfort working in a fast-moving environment where priorities shift and ambiguity is the norm.
- Intellectual curiosity: the AI landscape changes weekly, and you keep up because you're genuinely interested.
Nice to have
- Experience with MCP (Model Context Protocol) or Agent-to-Agent (A2A) integration patterns.
- Familiarity with AI agent orchestration frameworks (LangGraph, CrewAI, or similar).
- Experience with fine-tuning, distillation, or structured output techniques for LLMs.
- History of contributing to open-source AI/ML tooling or libraries.