Senior AI Engineer

The Senior AI Engineer owns Lena's reasoning layer end-to-end: retrieval, grounding, evaluation, and the boundary between AI suggestions and governed actions.

What you'll work on

• Designing and improving RAG pipelines for grounding Lena's diagnostic reasoning in structured operational telemetry, device state, and product documentation.
• Building evaluation harnesses that measure groundedness, hallucination, refusal calibration, and action accuracy on every release.
• Setting the boundary between Lena's probabilistic reasoning and the platform's deterministic action layer - what she's allowed to do, when, and under what audit.
• Owning AI cost and latency budgets per workflow.
• Partnering with backend (.NET) and platform engineers to land changes safely.

You're a fit if

• You have 5+ years of ML / applied AI engineering experience.
• You've built and shipped production LLM systems (RAG, agents, structured outputs, evaluations) at a B2B SaaS company.
• You've owned a production RAG system end-to-end.
• You've built evaluation pipelines that ran on every release and caught real regressions.
• You've worked at a growth-stage AI-native SaaS company where AI was the primary product.

You probably aren't a fit if

• Your AI exposure stops at experimentation or coursework.
• You haven't deployed AI systems to customer production environments.
• You want a process-heavy environment where decisions go through committees.

Do you have experience in Startup experience?, * 5+ years in machine learning engineering, or 5+ years combined across ML and applied AI systems

• 2+ years building and shipping LLM-powered systems in a growth-phase AI SaaS company where AI was the product, not a side feature
• Hands-on experience with RAG systems including vector databases, embedding tuning, and retrieval optimization
• Experience building evaluation pipelines for LLM performance, hallucination, and reliability in production
• Strong Python with production-level ML system implementation
• Track record operating under real product constraints: latency, cost, observability, and safety
• Comfortable being accountable for AI behavior in production

Strong signal

• Designed agentic workflows with measurable performance improvements
• Worked at AI-native startups that scaled from early traction to growth stage
• Reduced hallucination and improved grounding in production systems
• Cost optimization at scale, including token modeling and caching strategies
• Familiarity with compliance-aware AI logging and enterprise audit requirements
• Defined evaluation pipelines before feature release rather than after

Not the right fit if

• Your LLM experience is limited to experimentation, side projects, or non-production systems
• You are a backend engineer looking to pivot into AI
• Your background is research-focused without production ownership
• Your AI work has not operated under real customer impact

We are growth-stage and fully remote, not late-stage. We invest in the work, the tools, and the people, not the manifesto.

What that looks like in practice:

• Flexible / unlimited time off
• Health insurance
• Equity participation, discussed at offer
• Fully remote
• Architectural ownership of work that ships to real enterprise customers
• Direct working relationships with the people setting platform strategy
• A growth-stage platform where the decisions you make in your first year shape the product for years
• AI-assisted tooling licensed by NetSpeek (Cursor, Claude Code, GitHub Copilot, or comparable)