🚀 Hermes Web: Call for Founding Engineer

Hermes Web is looking for a founding engineer to build the first polished, hosted personal AI agent product.

Some facts about us:

• Incubated by Open Core Ventures, the studio founded by Sid Sijbrandij (ex-CEO of GitLab)
• Building the hosted, non-technical-user version of Hermes Agent — the fastest-growing open-source agent framework after OpenClaw
• OCV underwrites infrastructure and LLM costs, so you optimize for growth and polish, not unit economics
• Fully remote, product-focused, compressed sprint cadence

If you want to own product and engineering end-to-end, ship consumer-grade polish in a space that's still raw, and help define what a mainstream AI agent product looks like, this is for you.

Project described below.

Requirements

• High agency, ship fast without hand-holding
• Strong Python skills — FastAPI or similar production web framework experience required
• Strong frontend skills (React, Next.js, TypeScript) for the chat, memory, and activity surfaces
• Experience with auth, billing, and multi-tenancy in production products
• Container orchestration experience (Kubernetes, Nomad, ECS, or equivalent)
• Experience with AI-native tools (Cursor, Claude Code, model APIs)
• Knowledge of agents, LLM gateways, rate limiting, and abuse prevention
• Comfortable working across frontend, backend, infrastructure, and AI workflows

The kind of person we want: someone who has shipped a consumer or prosumer product they're still proud of, and who responds to an aggressive timeline with "tight but doable if we cut X, Y, Z" rather than "let me spec it first."

Bonus skills:

• Experience with agent frameworks (Hermes, OpenClaw, LangGraph)
• LLM gateway or proxy work
• Stripe subscription billing at scale
• Production experience hardening agentically-generated code
• OSS contributions
• Consumer AI product experience (Cowork, Cursor, or similar)

Project: Hosted Hermes Agent Platform

1. Introduction

We are building a multi-tenant hosted platform that gives anyone their own personal Hermes agent running in the cloud in under 60 seconds. No terminal, no API keys, no configuration. The agent persists, remembers them, and gets better over time.

This project includes:

• Per-user Hermes containers with network and storage isolation
• A warm pool provisioning system for instant signup-to-first-message
• A production-hardened chat, memory, and activity interface
• An LLM gateway that meters usage, enforces caps, and prevents abuse
• Bundled Claude Sonnet access — users never see an API key or model selector
• Stripe billing infrastructure and self-serve subscription flows

2. Requirements

Platform and provisioning

• Per-tenant container orchestration via Kubernetes or Nomad
• Warm pool pattern for sub-90-second provisioning
• Idle sleep and fast wake (under 2 seconds on incoming message)
• Persistent per-tenant memory and conversation storage
• Auth via Clerk or Auth0 (email + Google OAuth, email verification required)

Frontend

• React, Next.js, TypeScript, Tailwind, shadcn
• Multi-tenant chat, memory, and activity surfaces
• Graceful handling of connection loss, agent timeouts, container restarts
• Streaming responses, conversation history, new-thread flows

LLM gateway

• Proxy every Anthropic API call from every tenant container
• Hold Anthropic API keys server-side; tenant containers never see them
• Per-tenant metering with second-by-second granularity
• Hard daily and monthly cost caps
• Circuit breakers for runaway loops
• Ops kill switch for any tenant

Billing and ops

• Stripe subscription integration at $20/mo
• Self-serve upgrade, downgrade, cancel
• Internal ops dashboard for user management and anomaly response
• Runbooks for common failure modes

3. Non-Goals

• Developer-facing platform
• Self-hosted desktop or mobile apps
• Skills marketplace or plugin ecosystem
• Workflow builder, triggers, scheduled agents
• Team accounts, SSO, enterprise features
• Multiple LLM providers or model selection
• Bring-your-own API key
• Forking Hermes — we track upstream and contribute back

4. Prior Art

• Hermes Agent — the open-source framework we build the hosted experience on top of
• OpenClaw — the largest agent framework today and reference for community patterns and growth dynamics
• LangGraph Deep Agents — architecture patterns for stateful long-running agent workflows
• Anthropic MCP — server design patterns for tool interfaces and permission-aware context
• Cowork (Anthropic) — polish bar and UX patterns for non-technical AI agent products
• Cursor agent UI — interaction model for AI agents in consumer products

Who we are:

At Focused, we move quickly to deliver quality software that achieves client outcomes and meets their customer’s needs. We strategically partner with our clients to leverage our expertise in design and software, while our clients bring their own domain expertise. We work with a variety of clients from different industries, collaborating as we get new products to market, modernizing legacy systems, or helping teams learn the skills they need to be successful.   

Our values:

• Listen first • We are experts in product practices but life long learners in the domain of our customers. We research, collaborate, and understand. 
• Learn why • We ask questions and talk to users to understand problem spaces, objectives, and goals, which allows us to deeply invest and drive towards the outcomes of our clients. 
• Love your craft • We love diving into a variety of domains and solving problems.  We take pride in delivering value, in communicating progress, and guiding our clients to success.

At Focused, our Engineers are both practitioners and experts in their craft. This role would play a crucial role in shaping and implementing engineering best practices and ensuring the successful delivery of complex software projects. With clients, we develop trust and influence - we are unintimidated and unintimidating. With colleagues, we set the standard for how we deliver success for clients.

What would you be doing?

• Directly engage with clients and provide expertise through pair programming and development on LangChain / LangGraph powered applications
• Deep expertise in LangChain, LangGraph and LangSmith
• Lead teams through end-to-end delivery across the stack, from backend services to modern web UIs.
• Pair program daily with teammates and clients to share knowledge, improve code quality, and grow together.
• Practice TDD and continuous refactoring to ensure code is reliable, maintainable, and understandable.
• Guide architecture decisions to support scalability, observability, and performance.
• Collaborate closely with designers, product managers, and stakeholders to continuously deliver valuable software.
• Coach developers on the team through pairing, mentoring, and modeling healthy engineering culture.
• Influence technical direction beyond the team, working across client orgs and Focused’s internal practices to share lessons, shape approaches, and raise the collective bar.
• Stay curious through experimenting with new patterns in the GenAI space, share what works (and what doesn’t), and help evolve how we build AI-powered software.

We are excited about you, because you:

• You’re a hands-on, full stack engineer with a strong track record of delivering software in collaborative, agile environments.
• You’ve worked with LangChain (or similar agentic frameworks), and understand how to architect AI-native systems responsibly and effectively.
• You have experience leading engineering teams and feel confident mentoring and supporting other developers.
• You believe that code quality matters, and that TDD and pairing help build better systems and stronger teams.
• You’ve worked across multiple languages or frameworks (e.g., Python, Node, Java, React, Next.js) and are pragmatic about tool selection.
• You’re excited about what’s happening in the AI space but stay focused on delivering value.
• You have experience navigating complex organizations, building bridges across functions, and helping teams adopt modern development practices.
• You’re as comfortable in the code as you are in a client meeting and can translate technical risks and wins into language anyone can understand.
• You love to share what you’re learning and make the team around you better.

If you had worked at Focused over the last 3 months you may have:

• Paired with a teammate to build a document Q&A system using LangChain and OpenAI APIs
• Helped design an architecture that integrates LLM agents into a legacy enterprise workflow
• Refactored a flaky test suite to support continuous delivery with confidence
• Mentored a junior dev through their first pairing and TDD session
• Built and deployed a full stack GenAI MVP with a React frontend and FastAPI backend
• Facilitated an architecture spike to evaluate vector database options for semantic search
• Contributed a new section to our internal AI playbook
• Helped write this job req

What to know before you apply: 

• This role will require working in a client office in the greater Dallas, TX area three days per week and up to 20% travel within the United States.
• Focused is unable to sponsor or take over sponsorship of the employment Visa process at this time.
• The Colorado base salary range for this role is $175,000 - $250,000.

Job Description 

Buzz is revolutionizing the analytics and maintenance of power grid infrastructure through our advanced AI solutions. Our computer vision systems analyze critical infrastructure to enhance safety, reliability, and operational efficiency across the power grid network. We're seeking an experienced Machine Learning Engineer to help lead our computer vision initiatives. You'll drive the development of cutting-edge models for power grid analysis and provide a leadership anchor on a team of talented ML engineers.

Responsibilities

• Architect and lead end-to-end computer vision projects focused on: Equipment defect detection, Thermal anomaly identification, Vegetation encroachment monitoring, Surveillance of closed areas for human and animal intrusions
• Drive innovation by incorporating the latest advances in deep learning and generative AI to enhance model training, accuracy and reliability
• Develop production-grade Python libraries for the complete ML lifecycle
• Mentor team members and establish best practices for model development, evaluation, deployment, and monitoring
• Advocate for and uphold software quality standards within the ML team

Qualifications & Experience

• 7-10 years of industry experience in computer vision and machine learning
• Deep expertise in modern computer vision and deep neural networks including: Object detection, Semantic segmentation, Image classification, Similarity search, Vision language models
• Proven track record of deploying and maintaining ML models in production
• Expert proficiency in PyTorch, Lightning, OpenCV, and Scikit-Learn
• Proficiency in FastAPI and Pydantic
• Strong software engineering foundation including: Git version control, Test driven development (Pytest), CI/CD, ML devops, Python type hinting
• 2-3 years of proven leadership experience of technical teams

Desired Additional Experience

• Multi-modal computer vision 
• Custom object detection model development
• Generative models for data augmentation
• ML deployment on edge devices
• Extracting measurements from GIS and/or drone metadata enriched imagery
• Model quantization
• Systematic hyperparameter tuning

Additional information:

• This position does not include sponsorship for United States work authorization.