About Ryw

Ryw is a seed-funded, Houston-based AI startup building agentic software for enterprise teams in complex, document-heavy industries — organizations that manage thousands of documents, bids, invoices, and operational records as part of their daily work. Our founding team — two Ph.D. engineers with deep backgrounds in applied AI research and industrial systems — is building products that turn messy real-world data into structured, auditable decisions at scale. We recently closed our seed round (> 2 MM) and are assembling the engineering team that will carry us through Series A and beyond.

The Role

This is our first dedicated engineering hire. You'll join a team of four — two founders and two developers — and work directly on the systems, architecture, and engineering culture that will define this company technically.

You won't be handed a backlog. You'll help decide what goes on it. You'll own the backend platform behind our AI products: multi-agent orchestration, retrieval pipelines, document intelligence workflows, and the infrastructure that makes them reliable enough for enterprise clients to depend on every day. You'll sit in on client conversations, shape product direction, and have a direct path to engineering leadership as we scale.

We're looking for someone who has shipped LLM-powered systems to real production users — not prototypes, not demos. Someone who knows when to move fast and when to slow down and build it right.

What You'll Own

Agentic backend systems — multi-agent orchestration, memory architectures, tool-use pipelines, and structured output workflows across multiple product tracks
RAG pipeline design and evaluation — retrieval strategy, embedding selection, reranking, and systematic quality measurement that goes beyond intuition
Document intelligence — OCR, structured extraction, entity resolution, and conflict detection over noisy, heterogeneous real-world data
LLM evaluation and reliability — benchmarking pipelines, quality gates, regression testing, and the observability that gives the team genuine confidence in what we ship
Cloud infrastructure and cost discipline — serverless or containerized (chosen for the right reasons), with token budgeting, caching, and inference efficiency as a matter of habit
Early engineering culture — how we review code, make architecture decisions, onboard future engineers, and set the quality bar

What We're Looking For

Required:

5+ years of backend engineering with strong fundamentals: API design, async patterns, data modeling, service boundaries, systems thinking
2+ years building and shipping LLM-powered applications to real production users — with the track record to back it up
Deep, hands-on experience designing and evaluating RAG pipelines — not just wiring up a vector store
Strong Python proficiency in production environments
Prompt engineering discipline: context management, structured outputs, failure handling, and honest assessment of model limitations
Cloud deployment experience (any major provider) — infrastructure decisions should feel like second nature
Familiarity with at least one agentic or LLM orchestration framework
Clear communication with both technical and non-technical audiences, written and verbal
Product instinct — you ask why before you ask how, and you push back constructively when something doesn't make sense

Strong signals:

Experience designing ingestion pipelines for unstructured, heterogeneous document sources
Knowledge graphs or graph-based data architecture
Enterprise data security, access control, and audit trail experience
Exposure to industrial, operational, or regulated-data environments
Early-stage startup or founding-team experience

This Role Is a Fit If

You've built serious backend systems and shipped LLM or RAG features into production — even if your title was never "AI Engineer"
You like working close to customers and turning messy, ambiguous workflows into reliable products
You move fluidly between architecture, implementation, debugging, and product trade-offs
You care about reliability, observability, and clear thinking as much as speed
You want to be the person who defines how engineering works at this company — not the person who follows the playbook

What Success Looks Like

In your first 90 days, you've strengthened the core platform behind at least one live product track. You've shipped reliable, customer-facing workflows — not internal prototypes. You've improved how we evaluate AI output quality and helped the team integrate new systems faster. The founders trust your architectural judgment, and future engineers will inherit a codebase you're proud of.

Compensation & Growth

Competitive base salary benchmarked against senior AI engineering market rates
Early-employee stock option grant with standard; sized to reflect that you're helping build this from the ground floor
Clear path to Staff Engineer or engineering leadership, with full comp renegotiation at conversion milestones
Houston hybrid preferred; open to remote with Central Time overlap and occasional travel

We're early stage. If you're the right person, we'll build the right package.

How to Apply

Send your resume or LinkedIn profile to agent@ryw.ai along with a short 45s video/note about a production AI system you built and shipped. Bonus points if you can tell us about something that broke and how you handled it.

We care more about what you've delivered than where you've worked.

Founding Engineer

Benefits