Interested in this AI/ML Engineer role at Harper?
Apply Now →Skills & Technologies
About This Role
Staff Engineer, Engineering Productivity \& AI Quality
==========================================================
Harper is an AI\-native commercial insurance company, based in San Francisco and built from scratch. Most knowledge work is judgment locked inside people's heads — the exceptions, the precedents, the decision traces no one ever wrote down. Converting that judgment into software is one of the largest human\-to\-computational transitions still in front of us, and we think the most honest place to prove it is the hardest one: commercial insurance, a trillion\-dollar industry that is still, even now, more than 90% done by hand. We're not patching legacy workflows or adding a copilot to them. We're rebuilding the business so that AI does the work and people do the judgment that AI can't yet — and then teaching it that, too.
It's working: \~1,000 new customers a month and roughly 100x growth in the past year. That pace sets the culture. We're on\-site in San Francisco, in the building together, working long days to high standards — because a rebuild this large doesn't happen part\-time or by committee. Almost no one joins Harper because they're passionate about insurance. They join because they want to be on the frontier of the AI transition, doing the most consequential work of their career, in a company being built to define a category rather than join one. If that's the work you're looking for, insurance is just where you get to do it.
The role
------------
Every great AI company ends up building the same invisible machine: the harnesses, tests, instructions, and review loops that let a small team ship with impossible leverage. At Harper that machine is existential. Our agents write code, serve customers, assemble submissions, and make decisions that move revenue — and AI\-generated code volume has pulled the scaling problem forward. Even with a 20\-person engineering team, our coding agents create the surface area, review burden, and architectural drift of a 100\-person org. If the rails are strong, twenty engineers operate like a hundred; if they're weak, velocity turns into drag and the CTO becomes the rail — which doesn't scale. This is the founding seat for that machine. You'll turn the CTO's taste into systems — PR preflight, integration tests, architecture rules, agent instructions, eval gates, the feedback loops every engineer feels daily — across three sub\-disciplines: Harness Engineering (the meta\-harness over our frontier coding agents, OpenClaw, Hermes, and internal agents), Developer Experience (CI/CD gates, build caching, merge queues, dev/staging/CI parity, the internal platform, eval infrastructure), and AI Quality (eval suite design, golden datasets, LLM\-as\-judge graders, production trajectory monitoring, drift detection, anti\-slop guardrails). The mission is simple: make the right way the easy way, and make Harper's engineering org compound with every ship.
What you'll own
-------------------
- CI/CD quality gates across Harper's most critical services — the minimum bar before code can merge.
- Integration test harnesses anchored to real failure modes — every repeated operational failure becomes a regression test, a validation, or an architecture rule.
- The agent harness substrate — sandbox lifecycle, tool routing, prompt/context layer, model\-provider abstraction, multi\-agent coordination.
- Repo\-level agent instructions and context hygiene — AGENTS.md per repo, canonical data\-model docs, banned patterns. The information environment our coding agents read.
- Automated PR preflight — service\-impact summary, tests run, missing tests, model/migration changes, critical\-path warnings. The robot that reviews every PR before a human does.
- Architecture\-rule enforcement — custom lints and structural tests that encode the CTO's taste mechanically. Once a rule is written down, it never gets argued in PR comments again.
- Eval framework infrastructure — pre\-merge eval gating, experiments against curated datasets, production trajectory monitoring, all wired together.
- Engineering metrics that matter — rework rate, escaped defects, flaky\-test count, deploy rollbacks, time\-to\-confident\-ship, AI\-generated PR quality. Anti\-vanity, anti\-LOC.
What we're looking for
--------------------------
- 8\+ years building software, including Senior\+ scope at a high\-growth company (8–12 years total, 3\+ at Senior\+).
- A track record of building developer\-productivity, platform, CI/CD, build, test\-infra, or internal tooling that other engineers actually adopted.
- You write and review production code at a Staff level — this is not a process or PM role.
- Production AI/ML systems experience (agent harness, eval frameworks, LLM\-as\-judge graders, prompt/context engineering), even if it's not your primary stack.
- Strong opinions on maintainability, architecture, testability, and DX — backed by mechanical enforcement, not lectures. Excited by AI coding agents, skeptical enough to build the guardrails they need.
- You can describe a specific lint rule, integration test, or eval\-harness pattern you built that kept a class of bugs out of production for good.
- You write code with AI daily and routinely run 3\+ parallel sessions, and you'd rather create leverage for other engineers than own one product surface.
- Strong written communication (RFCs, architecture\-rule docs, lint\-rule rationale, playbooks).
- Bonus: eval\-framework infrastructure (OSS or internal); developer platforms at an AI\-native company; custom lint/structural\-test authoring at scale; agent harnesses (sandboxing, isolation, execution environments); encoding a CTO's architectural taste into mechanical rules.
If "Engineering Productivity" sounds like dashboards and roadmaps, this isn't it. We measure ourselves on rework prevented and confident\-ship time, not artifacts produced.
The reality
---------------
On\-site in San Francisco, in person, long days, high standards. This is a founding seat with founder and CTO access and a mandate to encode taste into systems the whole org runs on — which is high\-leverage and high\-scrutiny in equal measure. A rebuild this large doesn't happen part\-time or by committee. The right person reads the intensity as the reason to take the seat.
Logistics
-------------
- Compensation (OTE): $253,000–$308,000 cash (base \+ target performance bonus), plus competitive equity.
- Location: San Francisco, in\-office. Based here or willing to relocate.
- Benefits: Uber commuter benefits; breakfast, lunch, and dinner provided; snacks and coffee stocked; free gym membership; health, dental, and vision.
- Process: Founder call (15 min) CTO deep\-dive (60 min, architecture\-rule taste and eval\-harness depth) Super Day on\-site founder \+ CTO offer. No committee. Best offer, first.
To apply: If you want to be the engineer whose lint rules, test harnesses, and PR preflight checks let a 100\-person org run on a 25\-person team — send your resume, a link to a developer platform / eval harness / lint\-rule system you built, and tell us about an architectural drift you stopped before it reached production.
Compensation Range: $253K \- $308K
Salary Context
This $253K-$308K range is above the 75th percentile for AI/ML Engineer roles in our dataset (median: $180K across 2064 roles with salary data).
View full AI/ML Engineer salary data →Role Details
About This Role
AI/ML Engineers build and deploy machine learning models in production. They work across the full ML lifecycle: data pipelines, model training, evaluation, and serving infrastructure. The role has evolved significantly over the past two years. Where ML Engineers once spent most of their time on model architecture, the job now tilts heavily toward inference optimization, cost management, and integrating LLM capabilities into existing systems. Companies want engineers who can ship production systems, and the experimenter-only role is fading fast.
Day-to-day, you're writing training pipelines, debugging data quality issues, setting up evaluation frameworks, and figuring out why your model performs differently in staging than it did on your dev set. The best ML engineers are obsessive about reproducibility and measurement. They instrument everything. They know that a model is only as good as the data feeding it and the infrastructure serving it.
Across the 3,963 AI roles we're tracking, AI/ML Engineer positions make up 70% of the market. At Harper, this role fits into their broader AI and engineering organization.
Demand for AI/ML Engineers has been strong and consistent. Unlike some AI roles that spike with hype cycles, ML engineering is a foundational need. Every company deploying AI models needs people who can keep them running, and the gap between research prototypes and production systems keeps growing.
What the Work Looks Like
A typical week might include: debugging a data pipeline that's silently dropping 3% of training examples, running A/B tests on a new model version, writing documentation for a feature flag system that lets you roll back model deployments, and reviewing a junior engineer's PR for a new evaluation metric. Meetings tend to be cross-functional since ML touches product, engineering, and data teams.
Demand for AI/ML Engineers has been strong and consistent. Unlike some AI roles that spike with hype cycles, ML engineering is a foundational need. Every company deploying AI models needs people who can keep them running, and the gap between research prototypes and production systems keeps growing.
Skills Required
Python and PyTorch dominate the requirements. Most roles expect experience with cloud platforms (AWS, GCP, or Azure) and familiarity with ML frameworks like TensorFlow or JAX. RAG (Retrieval-Augmented Generation) has become a top-3 skill requirement as companies integrate LLMs into their products. Docker and Kubernetes show up in about a third of postings, reflecting the production focus of the role.
Beyond the core stack, employers increasingly want experience with experiment tracking tools (MLflow, Weights & Biases), feature stores, and vector databases. Fine-tuning experience is valuable but less common than you'd think from reading Twitter. Most production LLM work is RAG and prompt engineering, not fine-tuning. If you have both, you're in a strong position.
Companies that are serious about AI/ML hiring tend to post specific infrastructure details in the job description: the frameworks they use, their model serving stack, their data pipeline tools. Vague postings that just say 'ML experience required' without specifics are often companies that haven't figured out what they need yet.
Compensation Benchmarks
AI/ML Engineer roles pay a median of $180,000 based on 12,398 positions with disclosed compensation. Senior-level AI roles across all categories have a median of $227,400. This role's midpoint ($280K) sits 56% above the category median. Disclosed range: $253K to $308K.
Across all AI roles, the market median is $200,000. Top-quartile compensation starts at $253,000. The 90th percentile reaches $307,500. For comparison, the highest-paying categories include AI Engineering Manager ($290,000) and AI Safety ($274,200). By seniority level: Entry: $97,760; Mid: $163,400; Senior: $227,400; Director: $244,800; VP: $250,000.
Harper AI Hiring
Harper has 2 open AI roles right now. They're hiring across AI/ML Engineer. Based in San Francisco, CA, US. Compensation range: $253K - $308K.
Location Context
AI roles in San Francisco pay a median of $253,000 across 2,103 tracked positions. That's 26% above the national median.
Career Path
Common paths into AI/ML Engineer roles include Data Scientist, Software Engineer, Research Engineer.
From here, career progression typically leads toward ML Architect, AI Engineering Manager, Principal ML Engineer.
The fastest path into ML engineering is through software engineering with a self-directed ML education. A CS degree helps, but production engineering skills matter more than academic credentials. Build something that works, deploy it, and measure it. That portfolio project is worth more than a Coursera certificate. For career growth, the fork comes around the senior level: go deep on technical complexity (staff/principal track) or move into managing ML teams.
What to Expect in Interviews
Expect system design questions around ML pipelines: how you'd build a training pipeline for a specific use case, handle data drift, or design A/B testing infrastructure for model deployments. Coding rounds typically involve Python, with emphasis on data manipulation (pandas, numpy) and algorithm implementation. Take-home assignments often ask you to build an end-to-end ML pipeline from raw data to deployed model.
When evaluating opportunities: Companies that are serious about AI/ML hiring tend to post specific infrastructure details in the job description: the frameworks they use, their model serving stack, their data pipeline tools. Vague postings that just say 'ML experience required' without specifics are often companies that haven't figured out what they need yet.
AI Hiring Overview
The AI job market has 3,963 open positions tracked in our dataset. By seniority: 116 entry-level, 1,875 mid-level, 1,532 senior, and 440 leadership roles (Director, VP, C-Level). Remote roles make up 15% of the market (593 positions). The remaining 3,349 roles require on-site or hybrid attendance.
The market median for AI roles is $200,000. Top-quartile compensation starts at $253,000. The 90th percentile reaches $307,500. Highest-paying categories: AI Engineering Manager ($290,000 median, 39 roles); AI Safety ($274,200 median, 52 roles); Research Engineer ($260,000 median, 421 roles).
Demand for AI/ML Engineers has been strong and consistent. Unlike some AI roles that spike with hype cycles, ML engineering is a foundational need. Every company deploying AI models needs people who can keep them running, and the gap between research prototypes and production systems keeps growing.
The AI Job Market Today
The AI job market spans 3,963 open positions across 15 role categories. The largest categories by volume: AI/ML Engineer (2,783), Data Scientist (297), AI Software Engineer (279). These three account for the majority of open positions, though smaller categories often have higher per-role compensation because of specialized skill requirements.
The seniority mix tells a story about where AI teams are in their maturity. Entry-level roles (116) are outnumbered by mid-level (1,875) and senior (1,532) positions, reflecting that most companies are past the 'build a team from scratch' phase and need experienced engineers who can ship production systems. Leadership roles (Director, VP, C-Level) total 440 positions, representing the bottleneck between technical execution and organizational strategy.
Remote work availability sits at 15% of all AI roles (593 positions), with 3,349 requiring on-site or hybrid attendance. The remote share has stabilized after the post-pandemic correction. Senior and specialized roles (Research Scientist, ML Architect) are more likely to be remote-eligible than entry-level positions, partly because experienced hires have more negotiating power and partly because these roles require less hands-on mentorship.
AI compensation is structured in clear tiers. The market median sits at $200,000. Top-quartile roles start at $253,000, and the 90th percentile reaches $307,500. These figures include base salary with disclosed compensation. Total compensation (including equity, bonuses, and sign-on) runs 20-40% higher at companies that offer those components.
Category matters for compensation. AI Engineering Manager roles lead at $290,000 median, while Prompt Engineer roles sit at $140,000. The spread between highest and lowest-paying categories reflects the premium on specialized technical skills versus broader analytical roles.
The most in-demand skills across all AI postings: Python (2,043 postings), Aws (1,241 postings), Azure (934 postings), Rag (886 postings), Gcp (774 postings), Pytorch (614 postings), Prompt Engineering (614 postings), Claude (564 postings). Python dominates, appearing in the vast majority of role descriptions regardless of category. Cloud platform experience (AWS, GCP, Azure) is the second most common requirement. The newer entrants to the top skills list (RAG, vector databases, LLM APIs) reflect the shift from traditional ML toward generative AI applications.
Frequently Asked Questions
Get Weekly AI Career Intelligence
Salary data, skills demand, and market signals from 16,000+ AI job postings. Every Monday.