Senior AI Builder

EarnIn•Mountain View, CA

41d•$228,000 - $279,000•Hybrid

About The Position

EarnIn is seeking an AI builder who writes strong software to make AI-native engineering a core capability across the company. This role works at the intersection of platform engineering, developer experience, and applied AI, partnering with architects, domain leads, and product engineers to build tools, patterns, and guardrails that enable fast, safe, and durable AI adoption. Agents and harnesses built in this role will run in production and make decisions affecting EarnIn members. The position focuses on designing production agent infrastructure, rethinking the product development lifecycle with agentic workflows, owning evaluation infrastructure, and turning successful experiments into reusable production solutions. The role is hybrid in Mountain View, California, with in-office work required two days per week. The stated base salary range is $228,000–$279,000, plus equity and benefits.

Requirements

At least 4 years of full-time software engineering experience, including at least 2 years building tooling, platforms, or internal developer products.
Bachelor’s, Master’s, or PhD in Computer Science, Computer Engineering, or a related technical discipline, or equivalent industry experience.
Hands-on experience with LLM integration patterns, including prompt engineering, RAG pipelines, tool or function calling, and agent architectures.
Proficiency and comfort working across the stack when needed.
Experience with MCP, LangChain, or comparable orchestration frameworks.
Experience with open-source LLM models.
Strong opinions about developer experience and a track record of building products or tools that other engineers use.

Nice To Haves

Hands-on experience with reinforcement learning, especially RLHF, RLAIF, or reward modeling in applied product contexts.
Experience in fintech or regulated or security-sensitive environments.
Hands-on work with AI governance, including bias evaluation, audit logging, or model cards.
Exposure to multi-step reasoning pipelines or human-in-the-loop system design.

Responsibilities

Design agents, including prompts, reasoning chains, tool calls, and supporting architecture.
Build production infrastructure such as MCP servers, agent scaffolding, context harnesses, and a Skills Marketplace.
Rethink product development lifecycle stages from scoping and design through review, testing, deployment, and monitoring, replacing manual friction with agentic workflows where appropriate.
Build evaluation pipelines, automated pull request hygiene, deployment gates, and generation-to-merge metrics.
Own evaluation infrastructure, including pipelines, benchmarks, and quality gates to assess AI performance, degradation, and readiness to ship.
Design evaluation harnesses for AI-assisted workflows and establish generation-to-merge and review-latency baselines.
Make model quality visible and trustworthy across teams.
Turn successful engineering experiments into production-ready solutions that other teams can adopt.
Build reusable libraries, templates, and reference implementations for AI integration.
Document and develop harnesses that are actively used across engineering teams.