The Opportunity
Reflow is building the first AI-powered platform for hardware product development. This platform listens across the tools teams already use, maintains a structured picture of every program, and proactively coordinates across disciplines when things inevitably change. This role is for a hands-on AI engineer to design and build the agents at the core of our platform, backed by a parent company with deep roots in engineering and manufacturing. You will own the AI systems that set our product apart: agents that understand hardware workflows, anticipate problems, and take action on behalf of engineering teams.
Who We're Looking For
We are seeking an AI engineer proficient in both applied research and production software. The ideal candidate has shipped LLM-powered agent systems to real users, possesses strong intuitions about prompt engineering, tool use, and orchestration patterns, and stays current with the rapidly evolving field of AI. You should be comfortable evaluating new frameworks, models, and techniques and making pragmatic build-vs.-adopt decisions. While we currently use LangChain's DeepAgent, understanding how agent systems work under the hood, beyond just one framework's abstractions, is crucial. This senior engineer will collaborate with the engineering team and head of product to build, optimize, and operate AI agents that provide proactive coordination, risk surfacing, status summaries, and AI-generated deliverables. This is a hands-on role involving daily coding, contributing to AI architecture decisions, and defining agent capability evaluation and evolution.
What You'll Do
- Designing, building, and iterating on LLM-powered agents that coordinate across engineering disciplines, surface project risks, and generate structured deliverables (proposals, SOWs, status reports).
- Owning the agent orchestration layer (currently LangChain DeepAgent) and continuously evaluating whether to extend, replace, or supplement it as new frameworks and patterns emerge.
- Implementing robust tool-use patterns that connect agents to external systems (project management tools, CAD/PLM platforms, communication channels) via APIs and integrations.
- Designing and tuning prompts, chains, and retrieval strategies to maximize agent reliability, accuracy, and usefulness across diverse hardware project contexts.
- Building evaluation and observability infrastructure for agent performance, including tracing, cost tracking, latency monitoring, and automated quality benchmarks.
- Developing streaming agent interfaces that surface real-time progress, reasoning transparency, and proactive alerts to end users.
- Staying current with rapid advances in LLMs, agent frameworks, and related tooling, and translating that awareness into actionable recommendations for the team.
- Collaborating with frontend engineers on the UX of AI-powered features and with backend engineers on data pipelines and API design.
- Contributing to AI architecture decisions, code reviews, and engineering best practices.
Technical Requirements
Must Have:
- 5+ years of production software engineering experience, with 2+ years focused on bringing LLM-based applications or agent systems to market.
- Demonstrated proficiency using AI coding tools (Cursor, Copilot, Claude, etc.) to accelerate development.
- Hands-on experience building and deploying agentic systems using frameworks such as LangChain/LangGraph, CrewAI, AutoGen, or custom orchestration.
- Strong understanding of LLM fundamentals: prompt engineering, function/tool calling, retrieval-augmented generation (RAG), context window management, and token economics.
- Proficiency with Python in production environments.
- Experience integrating LLM-powered features with external APIs, databases, and third-party tools.
- Experience designing and operating background job / async task pipelines (Celery, RQ, Temporal, or similar) for long-running agent runs and reliable retries.
- Experience building multi-agent systems with planning, delegation, and inter-agent communication patterns.
- Demonstrated ability to evaluate and adopt new AI tools and frameworks quickly, with a track record of staying ahead of a fast-moving field.
- Strong software engineering fundamentals: clean architecture, testing, version control, and code review practices.
- Ability to balance rapid experimentation with production-grade reliability.
Highly Valuable:
- Direct experience with LangChain's DeepAgent or LangGraph for multi-step agent orchestration.
- Background in evaluation frameworks for LLM outputs (automated scoring, human-in-the-loop evaluation, regression testing for prompts).
- Familiarity with vector databases and embedding pipelines (Pinecone, Weaviate, pgvector, or similar).
- Experience with model serving infrastructure, fine-tuning workflows, or model selection/routing strategies.
- Understanding of authentication/authorization patterns (OIDC, JWT) and secure handling of user data in LLM contexts.
- Background in B2B SaaS platforms, project management tools, or technical collaboration products.
- Familiarity with hardware development, engineering workflows, or project management concepts (phases, gates, dependencies, requirements traceability).
- TypeScript / React fluency, enough to pair with frontend engineers on streaming agent UIs and reasoning-transparency surfaces.
What We Offer
- Real Impact: The opportunity to build purpose-built tooling for an entire industry that has never had it.
- Customer Access: Direct exposure to hundreds of real hardware projects annually through Re:Build's engineering and manufacturing companies.
- Technical Growth: Hands-on work at the frontier of applied AI, solving novel agent design challenges with real-world feedback loops.
- Autonomy: Backed by Re:Build while operating with startup independence.
- Benefits: Full health/dental/vision, bonus program, generous 401K, paid time off, annual learning stipend.
- Equity & Growth: Participation in Re:Build's LTIP equity program and opportunity for founder equity in potential spin-out.