Senior AI Engineer

About Unblocked

About Unblocked Unblocked is a high-growth, well-funded SaaS company that answers questions software teams have about their code, so engineers can spend less time in meetings and more time shipping.

We’re a small team with a track record of building developer tools that solve real problems. You’ll help define Unblocked, shape its roadmap, build the experiences customers love, and get firsthand feedback from the teams who use what we ship.

You’ve built and shipped products that engineers love, including the pipelines and services behind them.

You live in contemporary AI developer tools:
Claude Code, Cursor, agentic CLIs, MCP servers, and you have strong opinions on where they shine and where they fall short. You want to raise the bar for AI developer experience across the industry.

As a Senior AI Engineer at Unblocked, you’ll help design, build, and scale the market’s best context engine. Working alongside experienced engineers, you:

• Build and scale data pipelines and AI services that ingest and process large volumes of structured and unstructured data
• Design end-to-end LLM systems across prompting, context engineering, agent architectures, and evaluation frameworks
• Work across frontier models from Anthropic, OpenAI, Google, and open source, routing intelligently by capability, latency, and cost
• Design clean tool and context surfaces that agents can reliably reason and act over
• Obsess over developer experience. Our customers are engineers and expect that we push the bar higher with every release
• Influence the roadmap, mentor teammates, and continuously raise the technical bar for the whole team

• Based in Vancouver, BC, and willing to be in the office four days a week
• You’ve shipped production LLM applications at scale, not just notebook prototypes
• Hands‑on experience with context engineering: agentic retrieval, chunking, embeddings, reranking, graphs
• Hands‑on experience with frontier models across providers, with a view on when to reach for each
• A track record of building evaluation harnesses for non‑deterministic systems and using them to ship with confidence
• Expert familiarity with agentic coding environments
• Demonstrated leadership of teammates through the delivery of a project
• Experience architecting and shipping complex backend systems, ideally in AI/ML or data‑heavy domains

• Working knowledge of AI observability and eval tooling
• Expert‑level software development skills in a modern typesafe language
• You’ve built MCP servers, agent SDKs, or other developer‑facing AI infrastructure
• Experience with safety and guardrails for LLM systems, including prompt injection, PII handling, and untrusted content ingestion
• Eval‑driven optimization through distillation or fine‑tuning, where it actually pays off