Senior AI Engineer

Role overview

An early, hands-on engineering role building the AI agents at the core of a platform designed for hardware product development. The work focuses on designing LLM-powered systems that listen across existing tools, maintain a structured picture of every program, and proactively coordinate across engineering disciplines when changes occur.

Responsibilities

- Design, build, and iterate on LLM-powered agents that coordinate across disciplines, surface risks, and generate structured deliverables - Own the agent orchestration layer, evaluating whether to extend, replace, or supplement current frameworks as the landscape evolves - Implement tool-use patterns connecting agents to project management, CAD/PLM, and communication systems via APIs - Tune prompts, retrieval strategies, and chains to maximize reliability across diverse hardware project contexts - Build evaluation and observability infrastructure for tracing, cost tracking, latency monitoring, and automated quality benchmarks - Develop streaming agent interfaces that surface real-time progress and reasoning transparency to end users - Collaborate with frontend and backend engineers on AI-powered features, data pipelines, and API design - Stay current with advances in LLMs and agent frameworks and translate that awareness into team recommendations

Requirements

- 5+ years of production software engineering experience, with 2+ years focused on LLM-based applications or agent systems - Hands-on experience with agentic frameworks such as LangChain/LangGraph, CrewAI, AutoGen, or custom orchestration - Strong understanding of prompt engineering, function calling, retrieval-augmented generation, and token economics - Production proficiency with Python and experience integrating LLMs with external APIs and databases - Experience with background job and async task pipelines such as Celery, RQ, or Temporal - Demonstrated ability to evaluate and adopt new AI tools quickly and balance rapid experimentation with production-grade reliability - Strong fundamentals in clean architecture, testing, version control, and code review

Nice to have

- Experience with vector databases and embedding pipelines such as Pinecone, Weaviate, or pgvector - Familiarity with model serving, fine-tuning workflows, or model routing strategies - Understanding of authentication and authorization patterns like OIDC and JWT - Background in B2B SaaS, project management tools, or hardware development workflows - TypeScript and React fluency for pairing on streaming agent UIs

Benefits and work setup

- Remote-first with preference for candidates in Boston, Seattle, Los Angeles, or other cities with nearby offices - Base salary range of $143,666.72–$215,500.08 per year, plus potential annual incentive and long-term incentives - Comprehensive benefits including medical, dental, vision, retirement, paid time off, bonus program, 401K, and an annual learning stipend - Participation in a long-term incentive equity program and potential founder equity in a spin-out - Restricted to US citizens or lawful permanent residents due to export-controlled information