Senior full-stack AI engineer → San Francisco · Brazil

Joinplank; Brasil; On-site; BRL 300,000 - 600,000; Full time

Job summary

Joinplank is seeking a Senior AI Engineer to lead architecture and delivery on production AI engagements in San Francisco, translating business outcomes into technical plans and owning the value case and KPIs. You should have around 7+ years of engineering experience shipping production systems, with depth in LLM architecture (agents, RAG, evals, retrieval) and a track record of delivering outcomes.

You will mentor engineers, coordinate across teams, and partner with customer leadership to scope

Qualifications

• 7+ years of engineering experience shipping production systems
• Depth in LLM application architecture: agents, RAG, evals, retrieval
• Experience owning delivery and outcomes: scoping, ROI, stakeholder management
• Leadership: raises the bar across the team

Responsibilities

• Lead architecture and delivery on complex production AI engagements, owning trade-offs across scope, speed, and quality.
• Translate business outcomes into technical plans, and own the value case and KPIs for the deployment.
• Coordinate execution across engineers, and set the eval and quality strategy.
• Mentor engineers and raise the technical bar across the team.
• Partner with customer leadership to scope and de-risk deployments.

Skills

Production AI

LLM architecture

Stakeholder management

Leadership

Job description

Senior engineers set the technical bar on Plank pods and forward-deployed engagements: the architecture, the value case, and the hardest production AI problems. You translate business outcomes into technical plans, own the result, and raise the level of everyone around you.

What you will do

• Lead architecture and delivery on complex production AI engagements, owning trade-offs across scope, speed, and quality.
• Translate business outcomes into technical plans, and own the value case and KPIs for the deployment.
• Coordinate execution across engineers, and set the eval and quality strategy.
• Mentor engineers and raise the technical bar across the team.
• Partner with customer leadership to scope and de-risk deployments.

What we are looking for

• Around 7 plus years of engineering experience, with a track record of shipping and operating production systems.
• Depth in LLM application architecture: agents, RAG, evals, retrieval, and tool use.
• Experience owning delivery and outcomes, not just code: scoping, ROI, and stakeholder management.
• Leadership: you raise the bar of everyone around you.