Head of Engineering — Lazo (via Remotesome)

About Lazo

Lazo offers comprehensive tax, bookkeeping, and fundraising solutions for startup founders through expert-led services and AI Agents.

Our Lazo One platform, enhanced by our trademarked Augmented Ops™, streamlines every essential startup operation, optimizing critical tasks efficiently, while our expert team provides personalized strategic guidance, ensuring founders focus on growth while we handle the complexities.

From incorporation to scaling, we provide the strategic support founders need to grow their businesses. Backed by global partners like Google for Startups, AWS, EY, Endeavor, and Tampa Bay Wave, Lazo is the ultimate partner for startups seeking to scale with confidence.

The mission

Own and accelerate the engineering backbone that makes agentic AI safe, reliable, and cost-effective at scale. You’ll sit at the leadership table driving strategy and trade-offs, and still ship production code—building the reference architecture for agents, tool orchestration, evals, and the secure data plane that powers Lazo One.

Why this role is exciting

• Build agentic systems in production: orchestrate LLMs, toolchains, and human-in-the-loop flows.

• Own reliability & safety: SLOs, evals, guardrails, and SOC2-readiness for AI features.

• Be a player-coach: hire and mentor a scrappy engineering team while shipping key PRs yourself.

• Move fast with discipline: tight feedback loops, reproducible evals, and measurable product impact.

What you’ll own

Strategy & Architecture

• Define the reference architecture for agentic systems: LLM selection, tool orchestration, data plane, caching, and evals.

• Set tech strategy aligned to product OKRs, FinOps targets, and security/compliance goals.

• Present trade-offs, risks, and progress in leadership reviews and investor updates.

Hands-on Engineering

• Ship high-impact backend services in Python/TypeScript; lead code reviews and critical PRs.

• Orchestrate multi-agent toolchains (ADK/BeeAI/n8n-style flows), external API integrations, and reliable pipelines.

• Own end-to-end DevOps: IaC, containerization, CI/CD, observability, and on-call design.

• Improve throughput/latency and reduce infra cost per workflow.

Reliability, Safety & Data

• Define SLOs, error budgets, and incident runbooks; drive MTTR and change-fail-rate improvements.

• Implement AI safety guardrails, PII controls, secure data flows, and reproducible evals for model-driven features.

• Lead post-mortems and preventive engineering (chaos drills, playbooks).

Team & Process

• Hire, mentor, and scale a high-leverage engineering org; install Product Ops/DevOps best practices.

• Create scorecards (DORA, SRE, lead time) and embed them into weekly operating rhythms.

• Foster a culture of fast experiments, clear writing, and ownership.

How we measure success

• AI quality: reproducible eval suite + improving task success rates and safety metrics.

• Reliability: SLOs met, MTTR and CFR reduced, predictable incident playbooks.

• Cost & scale: infra cost per client/workflow trending down as usage grows.

• Delivery: faster lead times, higher deployment frequency, solid review SLAs.

• Team: faster ramp for new hires, high engagement, and clear technical mentorship.

30–60–90 day plan

• 30: Map current architecture, risks, and cost/security posture; ship first meaningful PR and define golden path for contributors.

• 60: Tech roadmap v1 with quarterly milestones; hardened CI/CD, improved test coverage; 1–2 agentic workflows running with basic evals.

• 90: SLOs & dashboards live; MTTR and CFR targets hit; priority tech-debt plan and first key hires onboarded.

Must haves

• 6–8+ years building & scaling software in growth-stage environments; 3+ years leading teams or as a player-coach.

• Strong backend chops (Python and/or TypeScript), containerization (Docker), cloud (AWS or GCP), IaC (Terraform/CDK), CI/CD.

• Hands-on experience with LLMs/agent orchestration and production evals; clear understanding of safety/guardrails and data flows.

• Observability & security fluency (OpenTelemetry or similar; IAM, secrets, hardening).

• Data-driven communicator with excellent written English.

Nice-to-haves

• FinOps, SRE, SOC 2/compliance, or finance/ops domain experience.

• Experience with ADK/BeeAI/n8n-style orchestrators, RAG pipelines, LangChain-like patterns, or Langfuse/LlamaIndex-style eval tooling.

• Spanish speaker; experience with distributed, cross-timezone teams.

Our stack

Python/TypeScript · AWS/GCP · Docker · IaC (Terraform/CDK) · Postgres/OLAP · GitHub Actions · OpenTelemetry · Agent orchestration tools · Feature flags · Secrets management

How we work

• Leadership cadence: weekly reviews + MBR/QBR; scorecards in Sheets/Monday.

• High ownership, fast feedback, and a bias for clear writing (PRDs & design docs > meetings).

• Small team, outsized impact—ship weekly, iterate fast, and improve continuously.

Required Skills

• LLM — Advanced
• Python — Advanced
• Typescript — Advanced

Compensation

$72K – $90K/year

Timezone: UTC-8 to UTC-5