Empirical is a new kind of product development partner — people-first at our core, AI-driven by design. We help tech companies build products that people love across four areas: AI-enabled product & tech leadership (advisory, coaching, and fractional models), end-to-end product development (concept to launch), nearshore AI-enabled team augmentation (high-performing Latin American talent that integrates with your workflows), and AI strategy & implementation consulting (finding where AI drives the most value in your product, operations, or customer experience).
We’re a people-first company grounded in empathy, integrity, and meaningful collaboration. From strategic planning to hands-on execution, we work alongside founders and teams to bring great products to life—without the noise.
Our Core Values
Care about people first
Strive to add value always
Lead with integrity
Have fun every step of the way
We are building a development pipeline for one of our clients where business users initiate work, AI agents implement it, and engineers review outcomes rather than steer execution. You will lead that build and own the machinery that makes it safe enough to run: the conventions, gates, identities, autonomy tiers, and measurements that determine whether AI-generated code is safe to merge.
Most engineering roles are measured on what you ship. This one is measured on what the pipeline ships. If a good week is one where you personally closed a lot of tickets, this role will frustrate you. If a good week is one where forty changes went through cleanly and you spent Thursday deleting a rule that had stopped earning its place, keep reading. The hard part of this job is not building the automation; it is refusing to trust it.
What You’ll Do
Own the knowledge plane: project conventions, reusable agent procedures, and source indexing so agents find every relevant call site, plus the enforcement that makes it all stick. This is the highest-leverage surface in the system.
Build gates that read artifacts: verification that inspects what actually happened (did the test file change, does coverage include the new branch) rather than trusting an agent’s account of its own work, including a protected path around tests and CI config.
Design authority and identity: least-privilege, short-lived agent credentials where an agent’s authority is the intersection of its own and its sponsor’s, never the union, with attribution from every commit back to a person, an agent, and a task.
Calibrate autonomy tiers: a classifier that routes changes by how hard they are to undo and fails toward caution. Copy changes merge themselves; schema migrations get a plan and a human. You will move the boundaries based on incident history, not optimism.
Engineer containment: circuit breakers that stop a repair loop from amplifying its own failures, per-workflow ceilings on tokens, wall-clock, retries and concurrency, progressive exposure, and rollback.
Own intake and measurement: the request surface with real reproduction context attached, deduplication and routing, plus a gate log that records every evaluation (passes included) and an evaluation harness so configuration changes are shown to be improvements, not assumed to be.
Run the improvement ritual: dated incident records, a threshold before a pattern becomes a rule, and a recurring pass that asks what each rule cost versus what it prevented. Removal is a first-class outcome.
Based in Latin America, with enough timezone overlap for daily collaboration with a U.S.-based engineering team.
10+ years in software engineering, including deep CI/CD and platform experience: you have built pipelines other engineers depend on, and you have been on the hook when one broke at 6pm on a Friday.
A genuinely strong engineer first: you cannot govern code you can’t read, and the person setting the standard for agent output has to be better than the agent, not worse.
Real security instincts without needing to be a security engineer: least privilege, credential scope, blast radius, untrusted input. “Any authenticated user can submit free text that an agent acts on with commit rights” should immediately worry you.
Testing judgment, not just testing habits: you have opinions about what makes a suite worth trusting, you have measured a flake rate rather than estimated one, and you distrust green builds until the artifacts back them up.
Hands-on agentic tooling experience: you have driven coding agents on real work, not demos, and you have a specific, unsentimental view of where they are strong and where they quietly fail.
Comfortable operating cross-functionally: several of the things you will need are owned by SRE, security, legal, and support teams that have never been in a pipeline conversation.
A willing writer: much of this job is prose (conventions, procedures, incident records, the argument for a rule). Think of it as documentation with a compiler attached.
Excellent communication skills in English (written and spoken).
Your best weeks are the ones where you personally shipped the most.
You want to “work on AI” in the sense of models and prompts. This is mostly plumbing, policy, and measurement; the model is somebody else’s product.
You would accept “the tests passed” as evidence that the tests ran.
You need the thing you own to be finished. It won’t be; it will be calibrated continuously against incidents that haven’t happened yet.
Full-time, dedicated client engagement with genuine ownership: this is a system, not a ticket queue, and the person who owns it makes the calls about how it works.
Executive sponsorship: the client has committed to this as an operating model change, not a tooling upgrade, which means protected time and no expectation that you also carry a feature roadmap.
An honest scope: low-risk changes end to end, higher-risk changes gated, and irreversible changes staying with humans for the foreseeable future.
Leverage that compounds: a rule you write today is enforced against every change for as long as it earns its place. Very little engineering work has that shape.
Be part of a curated network of high-caliber, values-driven professionals
Do meaningful, strategic work on your terms
Stay in motion without burnout
Access Empirical’s community, engineering talent, and shared knowledge base
Work with clients who value clarity, velocity, and outcomes—not just hours
Skills Required
- Based in Latin America with sufficient timezone overlap for daily collaboration with a U.S.-based engineering team
- 10+ years of software engineering experience
- Deep CI/CD and platform experience, including building and supporting pipelines used by other engineers
- Strong hands-on software engineering ability and capacity to read and assess production code
- Strong security instincts involving least privilege, credential scope, blast radius, and untrusted input
- Demonstrated testing judgment, including evaluating test reliability and measuring flake rates
- Hands-on experience using coding agents on real engineering work
- Ability to work cross-functionally with SRE, security, legal, and support teams
- Strong technical writing ability for conventions, procedures, and incident records
- Excellent written and spoken English communication skills
What We Do
We are product development company focused on helping entrepreneurs and their teams build successful products. We help them succeed by transforming product ideas into high quality working software solutions through innovation, embracing agile methodologies and delivering each project milestone on time and budget. We provide a professional and high quality option for companies in need of product development. Why us? We are product developers experts who understand the business side of your company as well as the technical aspects of your project. We become partners with our clients and we have full transparency throughout the process. We have high standards of the quality we deliver. We take every project as if it was our own.
