Mastra is hiring a Customer Engineer who operates at the intersection of production reality and core platform design.
This role blends forward deployment and core engineering. You will work directly with teams deploying agents in production and translate what you learn into improvements in the Mastra framework itself.
With Customers
Collaborate directly with customer teams building real agent systems
Design and implement agents alongside their engineers
Improve reliability, eval strategies, monitoring, and scaling approaches
Help teams move from prototype to durable systems
Train and upskill customers to become Mastra experts
Share patterns and best practices across accounts
When agents break or systems stall, you help make them stronger and more repeatable.
In the Core Framework
Turn recurring customer challenges into OSS improvements
Fix reliability and performance issues
Ship new primitives and refine existing ones
Raise the quality bar across the codebase
Contribute to roadmap direction through firsthand production insight
You’ll convert real-world friction into durable primitives.
This role is for engineers who:
Have built and operated AI systems in production
Can move from implementation details to system-level thinking
See patterns where others see one-off issues
Care deeply about developer ergonomics
Prefer ownership over narrow scope
You should be comfortable moving between hands-on customer collaboration and foundational platform design.
Most companies separate customer-facing engineering from core product engineering. We don’t. The best platform improvements come directly from real-world usage. This role exists to compress that loop. If you want to work on real systems and influence the primitives that define how agent infrastructure is built, this is that role.
1) Intro call with our recruiter
2) Hiring Manager Interview. Call with Shane Thomas, our co-founder and CPO, who leads customer engineering.
3) Peer Interview. Conversation with one of our customer engineers you'd be working alongside.
4) Take-home project `+ project review with our customer engineering team.
Mastra is the open-source TypeScript framework for building AI agents. Built by the team behind Gatsby, backed by Y Combinator and Spark Capital, with $35M raised total. We went from 0 to 28k+ stars and 2M+ weekly npm downloads in less than 2 years.
Small team, shipping fast, fully remote. Most of us work across North American and European time zones.
","descriptionPlain":"Mastra is hiring a Customer Engineer who operates at the intersection of production reality and core platform design.\n\nThis role blends forward deployment and core engineering. You will work directly with teams deploying agents in production and translate what you learn into improvements in the Mastra framework https://github.com/mastra-ai/mastra itself.\n\n\n\n\nWHAT YOU’LL OWN\n\nWith Customers https://mastra.ai/customers \n\n - Collaborate directly with customer teams building real agent systems\n\n - Design and implement agents alongside their engineers\n\n - Improve reliability, eval strategies, monitoring, and scaling approaches\n\n - Help teams move from prototype to durable systems\n\n - Train and upskill customers to become Mastra experts\n\n - Share patterns and best practices across accounts\n\nWhen agents break or systems stall, you help make them stronger and more repeatable.\n\nIn the Core Framework\n\n - Turn recurring customer challenges into OSS improvements\n\n - Fix reliability and performance issues\n\n - Ship new primitives and refine existing ones\n\n - Raise the quality bar across the codebase\n\n - Contribute to roadmap direction through firsthand production insight\n\nYou’ll convert real-world friction into durable primitives.\n\n\n\n\nWHO THIS IS FOR\n\nThis role is for engineers who:\n\n - Have built and operated AI systems in production\n\n - Can move from implementation details to system-level thinking\n\n - See patterns where others see one-off issues\n\n - Care deeply about developer ergonomics\n\n - Prefer ownership over narrow scope\n\nYou should be comfortable moving between hands-on customer collaboration and foundational platform design.\n\n\n\n\nWHY THIS ROLE IS DIFFERENT\n\nMost companies separate customer-facing engineering from core product engineering. We don’t. The best platform improvements come directly from real-world usage. This role exists to compress that loop. If you want to work on real systems and influence the primitives that define how agent infrastructure is built, this is that role.\n\n\n\n\nHIRING PROCESS\n\n1) Intro call with our recruiter\n\n2) Hiring Manager Interview. Call with Shane Thomas, our co-founder and CPO, who leads customer engineering. \n\n3) Peer Interview. Conversation with one of our customer engineers you'd be working alongside. \n\n4) Take-home project `+ project review with our customer engineering team. \n\n\nABOUT MASTRA\n\nMastra is the open-source TypeScript framework for building AI agents. Built by the team behind Gatsby, backed by Y Combinator https://www.ycombinator.com and Spark Capital https://www.sparkcapital.com, with $35M raised total. We went from 0 to 28k+ stars https://github.com/mastra-ai/mastra and 2M+ weekly npm downloads https://npmtrends.com/@mastra/core in less than 2 years. \n\nSmall team, shipping fast, fully remote. Most of us work across North American and European time zones.\n\n"},{"id":"531a3fe8-556f-4b83-bee7-20374f67f980","title":"AI Engineer ","department":"Engineering","team":"Engineering","employmentType":"FullTime","location":"Remote","secondaryLocations":[],"publishedAt":"2026-10-07T16:24:59.247+00:00","isListed":true,"isRemote":true,"workplaceType":"Remote","address":{"postalAddress":{}},"jobUrl":"https://jobs.ashbyhq.com/mastra/531a3fe8-556f-4b83-bee7-20374f67f980","applyUrl":"https://jobs.ashbyhq.com/mastra/531a3fe8-556f-4b83-bee7-20374f67f980/application","descriptionHtml":"We’re looking for an AI engineer. You’ll work on features that help developers understand their agents’ behavior, evaluate their performance, and improve them over time.
This is a hands-on engineering role. You’ll move between experiments, benchmarks, and product code, taking what you learn from evaluating agents and using it to shape the framework.
Why:
We’re starting to build more and more agentic features into Mastra: Trace intelligence, and we’re working on various Agent Learning features to automatically self-improve agents (Autoevals + Suggestions, Rollouts).
In addition, we’ve been increasingly running Mastra primitives like memory on industry-standard benchmarks and using the results to fine-tune configuration.
What you’ll do
Build the features that make this possible: tools for understanding traces, evaluating agent behavior, and turning results into improvements.
Run experiments on Mastra’s primitives, investigate where they perform well and where they fall short, and use those findings to improve their configuration and behavior. You’ll help turn that work into capabilities developers can use in their own applications.
You have:
Shipped agents and agentic applications into production
Tuned and tweaked them to improve accuracy
You need to be able to benchmark your results against existing datasets, or intelligently creating.
Mastra is the open-source TypeScript framework for building AI agents. Built by the team behind Gatsby, backed by Y Combinator and Spark Capital, with $35M raised total. We went from 0 to 28k+ stars and 2M+ weekly npm downloads in less than 2 years.
Small team, shipping fast, fully remote. Most of us work across North American and European time zones.
","descriptionPlain":"We’re looking for an AI engineer. You’ll work on features that help developers understand their agents’ behavior, evaluate their performance, and improve them over time.\n\nThis is a hands-on engineering role. You’ll move between experiments, benchmarks, and product code, taking what you learn from evaluating agents and using it to shape the framework.\n\nWhy:\n\n - We’re starting to build more and more agentic features into Mastra: Trace intelligence, and we’re working on various Agent Learning features to automatically self-improve agents (Autoevals + Suggestions, Rollouts).\n\n - In addition, we’ve been increasingly running Mastra primitives like memory on industry-standard benchmarks and using the results to fine-tune configuration.\n\nWhat you’ll do\n\nBuild the features that make this possible: tools for understanding traces, evaluating agent behavior, and turning results into improvements.\n\nRun experiments on Mastra’s primitives, investigate where they perform well and where they fall short, and use those findings to improve their configuration and behavior. You’ll help turn that work into capabilities developers can use in their own applications.\n\nYou have:\n\n - Shipped agents and agentic applications into production\n\n - Tuned and tweaked them to improve accuracy\n\n - You need to be able to benchmark your results against existing datasets, or intelligently creating.\n\n\nABOUT MASTRA\n\nMastra is the open-source TypeScript framework for building AI agents. Built by the team behind Gatsby, backed by Y Combinator https://www.ycombinator.com and Spark Capital https://www.sparkcapital.com, with $35M raised total. We went from 0 to 28k+ stars https://github.com/mastra-ai/mastra and 2M+ weekly npm downloads https://npmtrends.com/@mastra/core in less than 2 years. \n\nSmall team, shipping fast, fully remote. Most of us work across North American and European time zones.\n\n"}],"apiVersion":"1"}