{"schemaVersion":"jobsearcher.job.v1","id":"0e8064c4c96a3dc7eeacb671","url":"https://jobsearcher.com/jobs/0e8064c4c96a3dc7eeacb671","canonicalUrl":"https://jobsearcher.com/jobs/0e8064c4c96a3dc7eeacb671","title":"Software Engineer 3","description":"The Agent Research and Tooling team, part of MongoDB's AI Builder Experience organization, owns the platform layer around agents: how teams author, distribute, evaluate, monitor, and improve agent skills and agent behavior. We are hiring a software engineer to build and maintain the tooling, evaluation systems, and quality gates behind MongoDB's agent skills.\nThis is a software engineering role at the intersection of developer tooling, applied AI, and software quality. You will take loosely defined agent and tooling problems, break them into workable plans, and ship durable internal systems: command-line tools, reusable libraries, evaluation harnesses, and CI workflows.\nThis role is open to remote work in the US or can be based out of any of our US offices.\nWhat you'll do\nBuild and maintain agent skills and the infrastructure to validate, evaluate, publish, and maintain them\nDesign evaluation datasets and workflows that compare agent behavior against a baseline and produce actionable quality signals\nBuild agent metrics and observability: skill selection and routing, success and failure outcomes, tool calls, latency, and token usage\nDesign safety and quality gates for agent-authored content: rule packs, static analysis, confidence thresholds, structured verdicts, and bounded suppression\nCreate CLIs, libraries, and MCP integrations that other repositories adopt and that run in local development and CI\nIntegrate tooling into GitHub Actions and other CI workflows, including secrets, annotations, exit codes, and artifacts\nBuild code-generation quality checks, such as anti-pattern catalogs and linting for AI-generated MongoDB code\nInvestigate real failures such as nondeterministic results, false positives, and unsafe generated guidance, and turn them into reusable improvements\nCollaborate with engineers, security partners, and product teams; communicate trade-offs, risks, and ownership across teams\nExamples of the problems you'll solve\nHow can tests verify an agent tool's structured result when item order may vary, but counts, required fields, and values must remain correct\nHow can a CI gate flag unsafe instructions in an agent skill without treating every neutral mention as an incident or letting cautionary wording hide a real instruction\nHow can an evaluation suite show whether a skill improves answers over a baseline and give authors enough signal to improve it\nWhat we're looking for\n2+ years of experience building production software, developer tools, internal platforms, or automation systems\nSoftware engineering fundamentals in API design, testing, error handling, and maintainability\nExperience building CLIs, libraries, test infrastructure, static analysis, or CI/CD workflows\nAbility to design systems that are usable by developers and reliable in automation\nExperience reasoning about correctness and safety with ambiguous input, nondeterministic output, false positives, or untrusted content\nComfort in an evolving R&D environment where the right abstraction emerges through prototypes and feedback\nWritten and verbal communication, including explaining technical trade-offs and aligning stakeholders across teams\nNice to have\nExperience with agentic systems, LLM applications, prompt or rubric-based evaluation, or AI-assisted development\nExperience building eval harnesses, benchmark datasets, quality metrics, LLM-as-judge workflows, or human-review tooling\nExperience with Go, Python, JavaScript/TypeScript, Java, or C#\nExperience with GitHub Actions security, secret handling, static rule engines, or policy enforcement\nExperience moving prototypes into production\nWhat success looks like\nIn your first year, you will:\nShip tooling that makes agent skills or developer workflows easier to test, review, and adopt\nImprove the quality and interpretability of evaluations, not just their count\nConvert recurring manual work and fragile scripts into documented, reusable automation\nMake security, correctness, and operational trade-offs explicit in the designs you ship\nEarn adoption from partner teams through clear interfaces and reliable CI\nOwn projects independently while collaborating on shared systems\nAbout MongoDB\nMongoDB is built for change, empowering our customers and our people to innovate at the speed of the market. We have redefined the data platform for the AI era, enabling builders to create, transform, and disrupt industries with software. MongoDB's unified data platform, the most widely available, globally distributed data platform on the market, helps organizations modernize legacy workloads, embrace innovation, and unleash AI. Our cloud-native platform, MongoDB Atlas, is the only globally distributed, multi-cloud data platform and is available across AWS, Google Cloud, and Microsoft Azure.\nWith offices worldwide and over 67,000 customers, including 75% of the Fortune 100 and AI-native startups, relying on MongoDB for their most important applications, we're powering the next era of software.\nOur compass at MongoDB is our Leadership Commitment, guiding how and why we make decisions, show up for each other, and win. It's what makes us MongoDB.\nTo drive the personal growth and business impact of our employees, we're committed to developing a supportive and enriching culture for everyone. From employee affinity groups, to fertility assistance and a generous parental leave policy, we value our employees' wellbeing and want to support them along every step of their professional and personal journeys. Learn more about what it's like to work at MongoDB, and help us make an impact on the world!\nMongoDB is committed to providing any necessary accommodations for individuals with disabilities within our application and interview process. To request an accommodation due to a disability, please inform your recruiter.\nMongoDB, Inc. provides equal employment opportunities to all employees and applicants for employment and prohibits discrimination and harassment of any type and makes all hiring decisions without regard to race, color, religion, age, sex, national origin, disability status, genetics, protected veteran status, sexual orientation, gender identity or expression, or any other characteristic protected by federal, state or local laws.\nRed ID: 2273504602","company":"MongoDB","rawCompany":"mongodb","city":"Remote","state":"OR","isRemote":false,"isActive":false,"createdAt":"2026-08-10T15:25:50.916Z","occupations":[{"code":"15-1252.00","title":"Software Developers","slug":"software-developers"},{"code":"15-1253.00","title":"Software Quality Assurance Analysts and Testers","slug":"software-quality-assurance-analysts-and-testers"},{"code":"15-1299.08","title":"Computer Systems Engineers/Architects","slug":"computer-systems-engineers-architects"}],"industries":[{"code":"513210","title":"Software Publishers","slug":"software-publishers"},{"code":"541511","title":"Custom Computer Programming Services","slug":"custom-computer-programming-services"},{"code":"541512","title":"Computer Systems Design Services","slug":"computer-systems-design-services"}],"jobPosting":{"@context":"https://schema.org","@type":"JobPosting","title":"Software Engineer 3","description":"The Agent Research and Tooling team, part of MongoDB's AI Builder Experience organization, owns the platform layer around agents: how teams author, distribute, evaluate, monitor, and improve agent skills and agent behavior. We are hiring a software engineer to build and maintain the tooling, evaluation systems, and quality gates behind MongoDB's agent skills.\nThis is a software engineering role at the intersection of developer tooling, applied AI, and software quality. You will take loosely defined agent and tooling problems, break them into workable plans, and ship durable internal systems: command-line tools, reusable libraries, evaluation harnesses, and CI workflows.\nThis role is open to remote work in the US or can be based out of any of our US offices.\nWhat you'll do\nBuild and maintain agent skills and the infrastructure to validate, evaluate, publish, and maintain them\nDesign evaluation datasets and workflows that compare agent behavior against a baseline and produce actionable quality signals\nBuild agent metrics and observability: skill selection and routing, success and failure outcomes, tool calls, latency, and token usage\nDesign safety and quality gates for agent-authored content: rule packs, static analysis, confidence thresholds, structured verdicts, and bounded suppression\nCreate CLIs, libraries, and MCP integrations that other repositories adopt and that run in local development and CI\nIntegrate tooling into GitHub Actions and other CI workflows, including secrets, annotations, exit codes, and artifacts\nBuild code-generation quality checks, such as anti-pattern catalogs and linting for AI-generated MongoDB code\nInvestigate real failures such as nondeterministic results, false positives, and unsafe generated guidance, and turn them into reusable improvements\nCollaborate with engineers, security partners, and product teams; communicate trade-offs, risks, and ownership across teams\nExamples of the problems you'll solve\nHow can tests verify an agent tool's structured result when item order may vary, but counts, required fields, and values must remain correct\nHow can a CI gate flag unsafe instructions in an agent skill without treating every neutral mention as an incident or letting cautionary wording hide a real instruction\nHow can an evaluation suite show whether a skill improves answers over a baseline and give authors enough signal to improve it\nWhat we're looking for\n2+ years of experience building production software, developer tools, internal platforms, or automation systems\nSoftware engineering fundamentals in API design, testing, error handling, and maintainability\nExperience building CLIs, libraries, test infrastructure, static analysis, or CI/CD workflows\nAbility to design systems that are usable by developers and reliable in automation\nExperience reasoning about correctness and safety with ambiguous input, nondeterministic output, false positives, or untrusted content\nComfort in an evolving R&D environment where the right abstraction emerges through prototypes and feedback\nWritten and verbal communication, including explaining technical trade-offs and aligning stakeholders across teams\nNice to have\nExperience with agentic systems, LLM applications, prompt or rubric-based evaluation, or AI-assisted development\nExperience building eval harnesses, benchmark datasets, quality metrics, LLM-as-judge workflows, or human-review tooling\nExperience with Go, Python, JavaScript/TypeScript, Java, or C#\nExperience with GitHub Actions security, secret handling, static rule engines, or policy enforcement\nExperience moving prototypes into production\nWhat success looks like\nIn your first year, you will:\nShip tooling that makes agent skills or developer workflows easier to test, review, and adopt\nImprove the quality and interpretability of evaluations, not just their count\nConvert recurring manual work and fragile scripts into documented, reusable automation\nMake security, correctness, and operational trade-offs explicit in the designs you ship\nEarn adoption from partner teams through clear interfaces and reliable CI\nOwn projects independently while collaborating on shared systems\nAbout MongoDB\nMongoDB is built for change, empowering our customers and our people to innovate at the speed of the market. We have redefined the data platform for the AI era, enabling builders to create, transform, and disrupt industries with software. MongoDB's unified data platform, the most widely available, globally distributed data platform on the market, helps organizations modernize legacy workloads, embrace innovation, and unleash AI. Our cloud-native platform, MongoDB Atlas, is the only globally distributed, multi-cloud data platform and is available across AWS, Google Cloud, and Microsoft Azure.\nWith offices worldwide and over 67,000 customers, including 75% of the Fortune 100 and AI-native startups, relying on MongoDB for their most important applications, we're powering the next era of software.\nOur compass at MongoDB is our Leadership Commitment, guiding how and why we make decisions, show up for each other, and win. It's what makes us MongoDB.\nTo drive the personal growth and business impact of our employees, we're committed to developing a supportive and enriching culture for everyone. From employee affinity groups, to fertility assistance and a generous parental leave policy, we value our employees' wellbeing and want to support them along every step of their professional and personal journeys. Learn more about what it's like to work at MongoDB, and help us make an impact on the world!\nMongoDB is committed to providing any necessary accommodations for individuals with disabilities within our application and interview process. To request an accommodation due to a disability, please inform your recruiter.\nMongoDB, Inc. provides equal employment opportunities to all employees and applicants for employment and prohibits discrimination and harassment of any type and makes all hiring decisions without regard to race, color, religion, age, sex, national origin, disability status, genetics, protected veteran status, sexual orientation, gender identity or expression, or any other characteristic protected by federal, state or local laws.\nRed ID: 2273504602","datePosted":"2026-08-10T15:25:50.916Z","dateModified":"2026-08-10T15:25:50.916Z","hiringOrganization":{"@type":"Organization","name":"MongoDB","sameAs":"https://jobsearcher.com"},"jobLocation":{"@type":"Place","address":{"@type":"PostalAddress","addressLocality":"Remote","addressRegion":"OR","addressCountry":"US"}},"identifier":{"@type":"PropertyValue","name":"JobSearcher","value":"0e8064c4c96a3dc7eeacb671"},"url":"https://jobsearcher.com/jobs/0e8064c4c96a3dc7eeacb671"}}