AI Engineer

PeopleLoop

24d

About The Position

PeopleLoop is an AI-powered experience that modernizes benefits and PEO solutions for people-driven companies. It reduces complexity and errors across critical people operations, gives leaders clearer insight into compensation and benefits costs, trends, and tradeoffs, and delivers a more modern employee experience. In this role, you’ll build AI features that are embedded directly into the product experience. You’ll work on systems that use large models to ingest documents, support compliance reasoning, power personalized recommendations, and automate complex workflows. This is an applied AI role focused on shipping product using models, not training foundation models from scratch. As a Staff-level engineer, you’ll set patterns, mentor engineers, drive design reviews and RFCs, and help define how AI is built and operated across the product. Our backend is primarily Python, with supporting services in Node/TypeScript.

Requirements

7+ years of software engineering experience, with 2+ years at Senior or Staff level owning cross-team initiatives
Strong production experience building AI-powered product features using large language models or similar foundation models
Experience integrating and optimizing model endpoints in production
Strong Python experience, with working knowledge of modern backend or API development
Experience shipping features that use LLMs, retrieval, tool use, prompts, or structured outputs
Comfort working with large models and applying them to real product workflows
Experience improving latency, cost, reliability, and quality of AI systems
Ability to evaluate model performance with practical product metrics and user feedback
Strong collaboration skills and ability to work across Product, Design, and Engineering
Comfort building systems that balance automation with human review and control
Bachelor’s degree required, preferably in Computer Science, Engineering, or a related technical discipline; equivalent experience will be considered

Nice To Haves

Experience building AI features in benefits, HR tech, PEO, payroll, insurance, or other compliance-heavy domains
Familiarity with hosted LLM providers and model APIs
Experience with prompt engineering, retrieval-augmented generation, or agentic workflows
Experience with evaluation frameworks, observability, and feedback loops for AI products
Experience with structured extraction from documents or forms
Familiarity with graph-based or structured domain modeling
Human-in-the-loop systems, review queues, or approval workflows
Experience with multi-tenant or privacy-sensitive production systems
Comfort with product experimentation and rapid iteration on AI features

Responsibilities

Build AI-powered product experiences that help users complete complex workflows faster and with less friction.
Apply large models to real customer problems across admin, broker, and employee journeys.
Work directly with model endpoints and APIs, integrating hosted LLMs into production systems.
Tune latency, reliability, throughput, token usage, and cost while maintaining quality and trust.
Build and improve ingestion pipelines that use AI to extract and structure data from plan documents and related inputs.
Focus on practical performance, quality, and operational reliability.
Design AI features that produce grounded, traceable, and auditable outputs.
Make sure users can understand how recommendations were generated and what source data they are based on.
Use models and structured data to power tailored recommendations and decision support for employees, admins, and internal operators.
Develop systems that combine prompts, retrieval, and internal tools to produce useful outcomes.
Build guardrails, fallbacks, and structured output patterns that make model behavior dependable.
Create evaluation workflows to measure accuracy, grounding, completeness, and user impact.
Use offline tests, human review, and production feedback to continuously improve AI features.
Design workflows where the model assists users, but humans review, approve, and correct when needed.
Build systems that learn from feedback and improve over time.
Partner closely with Product, Design, and domain experts to identify where AI adds the most value, define acceptable failure modes, and turn ambiguous workflows into production-ready features.
Set engineering standards for AI feature development, mentor other engineers, and help establish the patterns that will scale AI across the product.