Test & Evaluation Lead

About Primordial Labs

We're building the next generation interface for commanding autonomous systems in the real world. Our core product, Anura, translates spoken or typed intent into structured actions across drones, sensors, and mission software—enabling faster, more intuitive control in high-stakes environments. We’re a distributed team of engineers, operators, and technologists focused on deploying reliable autonomy at the tactical edge.

The Mission

Anura takes a spoken order and turns it into robot motion. Proving that it works, in software, in simulation, and on real vehicles in the field, is one of the hardest and most important problems we have. We’re looking for someone to own that proof, and to build much of it themselves.

You’ll lead our quality assurance and physical test functions, and you’ll be hands-on with test development and infrastructure. You’ll build the automated test and evaluation capability that qualifies a build before it reaches a range, while setting the strategy, standards, and readiness criteria that tell us whether it’s ready. Much of our testing runs in simulation and hardware-in-the-loop environments, so you’ll design an approach that leans on them heavily.

When we tell a program office the system performs, the evidence behind that claim runs through you.

What You'll Do

• Set the Strategy. Define how we test, from automated suites on every build through simulation and system-level tests on real platforms, and what has to be true at each stage before a build moves forward.

• Build the QA Machinery. Design and build the automated test and evaluation capability, running on our simulation and HIL environments, along with the frameworks and standards our engineering teams test against. Range time is the most expensive test environment we have, and it should be confirming what you already know, not discovering it.

• Score the System. Build and maintain the end-to-end scenarios we measure system performance against, including hard cases designed to break things, from ambiguous commands and lost links to unexpected changes mid-mission. Measure whether the system did the right thing end to end, not just whether each component returned something plausible.

• Own the KPIs. Develop and own the test KPIs that define whether the system works for operators, built from acceptance criteria and mission-level performance measures. Track them across builds, measure where defects slip past our gates, and report results to leadership and customers.

• Own the Gates. Set the criteria a build must meet to enter physical test, and own the final sign-off on whether a build is ready to go to a customer, based on the evidence from QA and the range.

• Close the Loop. Turn field data from physical test into replayable regression cases and evaluation additions within days, not months.

• Lead the Team. Lead our physical test engineers, overseeing test planning, field events, and results, and grow the team as we scale. Expect occasional travel to test ranges and field events.

• Report the Truth. Produce clear test reports and readiness evidence for leadership, customers, and program offices, including results nobody wants to hear.

• Work Across the Org. Partner with systems engineering on acceptance criteria, with mission engineering on the measures that matter operationally, with the people building our simulation environments, and with DevOps on how tests run in the pipeline.

The Split

You and your team build the tests, run them, and tell us precisely what broke and under what conditions. Engineering owns the fixes. Test stays independent of the teams it evaluates, and protecting that independence is part of your job.

Who You Are

• Builder First. You write real code, and you’d rather build the test framework yourself than describe it to someone else.

• Suspicious by Default. You assume it’s broken until something proves otherwise, and you’re drawn to the failure mode nobody else thought to look for.

• Statistically Literate. You know a probabilistic system doesn’t pass or fail, it performs at a rate, and you can tell the difference between a real regression and noise.

• Independent and Credible. You can deliver an unwelcome result to engineering leadership or a customer and make it stick.

• Player-Coach. You lead by example, set clear standards, and grow engineers who would rather find the bug than defend the build.

• At Home Everywhere Test Happens. You’re as comfortable in a code review or a simulation environment as you are on a test range.

Required Qualifications

• Experience. 6+ years in QA, test engineering, test automation, or systems test, including experience leading engineers or test efforts.

• QA and Test Automation. Deep, hands-on experience building automated test suites and frameworks for complex software, and keeping them fast and trustworthy.

• Software. Strong proficiency in Python, comfort in Linux, and hands-on experience with CI.

• Test Leadership. Demonstrated experience defining test strategy, standards, KPIs, and readiness criteria for complex systems.

• System-Level Test. Working knowledge of testing on real hardware or platforms, and how field testing fits into a broader test strategy.

• Simulation. Familiarity with simulation and hardware-in-the-loop testing, and how to use them to reduce what has to be discovered in the field.

• Education. BS in Computer Science, Engineering, or a related technical field, or equivalent hands-on experience.

Nice to Have

• Experience building evaluation for ML models in production, including test set design, metric selection, and catching regressions that standard accuracy numbers hide

• Experience testing systems with ML components

• Robotics, unmanned systems, or autonomy test experience

• Defense test and evaluation experience, including test plans, TEMPs, and government deliverable reporting

• Experience building a test function at a startup or small company

Important Qualification Note: Due to the nature of our work and federal compliance requirements, this position strictly requires U.S. Citizenship and current residency within the United States. Please note that Permanent Residency (Green Card status) or visa sponsorship cannot satisfy these specific regulatory requirements.

Compensation

Compensation for this position includes a target base salary of $170,000 - $210,000 annually, with the specific figure determined by the candidate's experience level.

We’re committed to fair and equitable compensation and are happy to explain how we determine our salary ranges, just ask!

Our Benefits

• Beyond a Competitive Salary, we provide a significant equity stake, aligning your growth with ours.

• 100% Remote: This role is fully remote, open to residents across the US. We believe that talent knows no borders (well, except for the US in this case!).

• Comprehensive Health Coverage: We provide comprehensive medical, dental, and vision plans so you and your family can stay healthy and worry free.

• Retirement Planning: Plan for tomorrow with our 401(k) package, complete with a generous 6% company match.

• Generous DTO: Our generous Discretionary Time off (DTO) policy is all about helping you take the breaks you deserve and live your healthiest, most fulfilling life.

• Elite Technology Package: Enjoy an elite technology package to make your work effortless and efficient.

Our Interview Process

Our interview process is designed to be thorough and respectful of your time. It typically includes:

1. Conversation with the People Team: Lets get to know one another first!

2. Screener Interview: A 30-minute discussion about relevant concepts and your past experience.

3. Technical Challenge: We provide an at your own pace challenge focused on real life situations. After completion, you'll present your solutions in a follow-up call. This allows us to understand your thought processes and technical approach.

4. Technical Collaboration & Team Q&A: Walk through a recent code sample with the engineering team, discuss your design choices, and ask us anything about our stack, culture, and day to day work.

We are committed to a low-stress interview experience—no trick questions or brain teasers!

Primordial Labs is an equal opportunity employer, committed to creating a welcoming and respectful environment for everyone. Discrimination and harassment have no place here. We firmly believe that a diverse team enriches our problem-solving capabilities, sparks greater creativity, and ultimately leads to a better product and a more vibrant company.

We understand that great talent comes from various paths and that passion and transferable skills are invaluable. At Primordial Labs, what truly matters is your ability to make an impact, your dedication to our mission, and your capacity to thrive in a fast-paced, collaborative atmosphere. We are dedicated to fostering an inclusive workplace where you can contribute your unique talents, expand your skills, and learn continuously. If you’re driven to make a real impact, we encourage you to apply, even if your experience doesn’t perfectly align with every qualification.

#LI-REMOTE