{"schemaVersion":"jobsearcher.job.v1","id":"0f454fa78b7b8deda1dcdf1f","url":"https://jobsearcher.com/jobs/0f454fa78b7b8deda1dcdf1f","canonicalUrl":"https://jobsearcher.com/jobs/0f454fa78b7b8deda1dcdf1f","title":"Founding Engineer","description":"Full-stack product engineer who helps us build the AI platform for engineering consulting firms - agents that own entire professional workflows, starting with proposals.\n\nBuoyant is building the AI layer for engineering consulting firms - AEC, water, transportation, environmental. Our bet is that AI can own the dozen knowledge-heavy workflows these firms run every week: proposals, project kickoff, QA/QC, compliance filings, client communications. Anything that isn't the engineering itself is work an agent should do.\n\nToday's product is an AI agent that drafts proposals. It reads the RFP, researches the firm's past work, assembles a team, builds a strategy, and writes - grounded in the firm's real project history, in their voice. It lives inside Microsoft Word because that's where proposal teams already work. It's in production with customers who are winning work with it.\n\nWe're backed by $1M+ from Silicon Valley investors focused on AEC and climate. Proposals are the beachhead; what comes next is every other workflow these firms run. The founding engineer is joining at the point where the first agent has proven out and we're about to extend horizontally.\n\nWhat you'll do\n\nDay to day\nShip features customers are asking for this week\nThe roadmap is driven by what proposal managers need to win their next RFP - not what we think they might want next quarter.\n\nOwn the generation pipeline end-to-end\nBetter prompts, faster runs, lower cost, cleaner eval. You'll work across the full multi-stage LLM pipeline - content resolution, strategy, writing, compliance review, revision.\n\nExtend the knowledge base\nBetter search, better parsing, multi-modal support. Vector search, hybrid retrieval, document parsing - all open problems with direct customer impact.\n\nWork inside Microsoft Word\nThe primary authoring surface is a Word add-in. You'll build task panes, dialogs, and document manipulations that feel native to users who live in Word.\n\nTalk to customers\nEngineering firm principals are accessible and opinionated. You'll join calls, run demos, and turn their feedback into product.\n\nMake architectural calls\nWhat to build, what to buy, what to defer. This is a founding role - you'll own decisions that shape the codebase for years.\n\nWho you are\n\nWhat we're looking for\nMust-haves\n\nStrong TypeScript - the entire codebase is TypeScript. You're comfortable with strict typing, immutable data, and functional patterns.\n\nReact experience - both the web app (Next.js App Router) and Word add-in are React. Server components, hooks, state.\n\nLLM application development - not ML research, but building reliable systems on top of language models. Prompt engineering, structured extraction, RAG, eval.\n\nPostgreSQL - schema design, migrations, RLS. pgvector is a bonus.\n\nA bias toward shipping - you care what users experience, not just what's technically elegant.\n\nStrong advantages\n\nOffice.js or Word add-in experience (rare and valuable).\n\nDocument processing - parsing PDFs, DOCX, and other formats into structured text.\n\nSupabase / Firebase / BaaS experience - understanding tradeoffs.\n\nPrior startup experience - comfort with ambiguity, fast iteration, wearing multiple hats.\n\nNot the right role if\n\nPure ML/AI researchers who want to train models.\n\nFrontend-only engineers who won't touch the backend (or vice versa).\n\nAnyone who needs a large team or established process to be productive.\n\nWhat you'll build\n\nProblems waiting for you\n01\n\nAgents that do senior-level work, end-to-end\nA proposal isn't one task - it's scope analysis, team assembly, strategy, writing, compliance review, revision. Design and build the multi-agent system that does all of it, grounded in a firm's real project history, at a quality level where a principal engineer will put their name on the output.\n\n02\n\nEvaluation infrastructure for agentic work\nIf an agent writes a 40-page proposal, how do you know it's good? Classical NLP metrics fail. LLM-as-judge has its own failure modes. Build the eval infrastructure that measures accuracy, compliance coverage, voice match, and strategic coherence - and catches regressions before they reach customers. Nobody has fully solved this.\n\n03\n\nContext engineering at institutional scale\nFirms have decades of documents - thousands of PDFs, resumes, past proposals, specifications. An agent writing about stormwater design in urban California needs the right ten of those, not the thousand closest matches. Better chunking, hybrid retrieval, re-ranking, per-firm learning - this is where the product wins or loses.\n\n04\n\nExtending one agent into a platform\nThe proposal agent is product one. Next is project kickoff, QA/QC review, compliance filings, client comms. Each is a new domain with its own data model, quality bar, and user workflow - but they share a foundation: the firm's knowledge, their voice, the evals. Build that foundation so new agents ship in weeks, not months.\n\n05\n\nHuman-AI collaboration inside the work surface\nMost AI products are a chat box. Ours lives where the work happens - in Microsoft Word, inline with the document, watching edits, learning from feedback. Design the interaction model that turns an agent from a tool you use to a teammate that earns trust over time.\n\n06\n\nThe evals flywheel\nEvery proposal a firm accepts, edits, or rejects is a training signal. Over time we can learn what makes a great proposal for this firm, in this discipline, to this client - and feed that back into the agent. That signal loop, properly built, is the moat. Help us build it.\n\n#J-18808-Ljbffr","company":"Buoyant","rawCompany":"buoyant","city":"Millbrae","state":"CA","isRemote":false,"isActive":false,"createdAt":"2026-10-09T03:44:24.966Z","occupations":[{"code":"17-2199.00","title":"Engineers, All Other","slug":"engineers-all-other"},{"code":"15-1252.00","title":"Software Developers","slug":"software-developers"},{"code":"15-1299.08","title":"Computer Systems Engineers/Architects","slug":"computer-systems-engineers-architects"}],"industries":[{"code":"513210","title":"Software Publishers","slug":"software-publishers"},{"code":"541511","title":"Custom Computer Programming Services","slug":"custom-computer-programming-services"},{"code":"541330","title":"Engineering Services","slug":"engineering-services"}],"jobPosting":{"@context":"https://schema.org","@type":"JobPosting","title":"Founding Engineer","description":"Full-stack product engineer who helps us build the AI platform for engineering consulting firms - agents that own entire professional workflows, starting with proposals.\n\nBuoyant is building the AI layer for engineering consulting firms - AEC, water, transportation, environmental. Our bet is that AI can own the dozen knowledge-heavy workflows these firms run every week: proposals, project kickoff, QA/QC, compliance filings, client communications. Anything that isn't the engineering itself is work an agent should do.\n\nToday's product is an AI agent that drafts proposals. It reads the RFP, researches the firm's past work, assembles a team, builds a strategy, and writes - grounded in the firm's real project history, in their voice. It lives inside Microsoft Word because that's where proposal teams already work. It's in production with customers who are winning work with it.\n\nWe're backed by $1M+ from Silicon Valley investors focused on AEC and climate. Proposals are the beachhead; what comes next is every other workflow these firms run. The founding engineer is joining at the point where the first agent has proven out and we're about to extend horizontally.\n\nWhat you'll do\n\nDay to day\nShip features customers are asking for this week\nThe roadmap is driven by what proposal managers need to win their next RFP - not what we think they might want next quarter.\n\nOwn the generation pipeline end-to-end\nBetter prompts, faster runs, lower cost, cleaner eval. You'll work across the full multi-stage LLM pipeline - content resolution, strategy, writing, compliance review, revision.\n\nExtend the knowledge base\nBetter search, better parsing, multi-modal support. Vector search, hybrid retrieval, document parsing - all open problems with direct customer impact.\n\nWork inside Microsoft Word\nThe primary authoring surface is a Word add-in. You'll build task panes, dialogs, and document manipulations that feel native to users who live in Word.\n\nTalk to customers\nEngineering firm principals are accessible and opinionated. You'll join calls, run demos, and turn their feedback into product.\n\nMake architectural calls\nWhat to build, what to buy, what to defer. This is a founding role - you'll own decisions that shape the codebase for years.\n\nWho you are\n\nWhat we're looking for\nMust-haves\n\nStrong TypeScript - the entire codebase is TypeScript. You're comfortable with strict typing, immutable data, and functional patterns.\n\nReact experience - both the web app (Next.js App Router) and Word add-in are React. Server components, hooks, state.\n\nLLM application development - not ML research, but building reliable systems on top of language models. Prompt engineering, structured extraction, RAG, eval.\n\nPostgreSQL - schema design, migrations, RLS. pgvector is a bonus.\n\nA bias toward shipping - you care what users experience, not just what's technically elegant.\n\nStrong advantages\n\nOffice.js or Word add-in experience (rare and valuable).\n\nDocument processing - parsing PDFs, DOCX, and other formats into structured text.\n\nSupabase / Firebase / BaaS experience - understanding tradeoffs.\n\nPrior startup experience - comfort with ambiguity, fast iteration, wearing multiple hats.\n\nNot the right role if\n\nPure ML/AI researchers who want to train models.\n\nFrontend-only engineers who won't touch the backend (or vice versa).\n\nAnyone who needs a large team or established process to be productive.\n\nWhat you'll build\n\nProblems waiting for you\n01\n\nAgents that do senior-level work, end-to-end\nA proposal isn't one task - it's scope analysis, team assembly, strategy, writing, compliance review, revision. Design and build the multi-agent system that does all of it, grounded in a firm's real project history, at a quality level where a principal engineer will put their name on the output.\n\n02\n\nEvaluation infrastructure for agentic work\nIf an agent writes a 40-page proposal, how do you know it's good? Classical NLP metrics fail. LLM-as-judge has its own failure modes. Build the eval infrastructure that measures accuracy, compliance coverage, voice match, and strategic coherence - and catches regressions before they reach customers. Nobody has fully solved this.\n\n03\n\nContext engineering at institutional scale\nFirms have decades of documents - thousands of PDFs, resumes, past proposals, specifications. An agent writing about stormwater design in urban California needs the right ten of those, not the thousand closest matches. Better chunking, hybrid retrieval, re-ranking, per-firm learning - this is where the product wins or loses.\n\n04\n\nExtending one agent into a platform\nThe proposal agent is product one. Next is project kickoff, QA/QC review, compliance filings, client comms. Each is a new domain with its own data model, quality bar, and user workflow - but they share a foundation: the firm's knowledge, their voice, the evals. Build that foundation so new agents ship in weeks, not months.\n\n05\n\nHuman-AI collaboration inside the work surface\nMost AI products are a chat box. Ours lives where the work happens - in Microsoft Word, inline with the document, watching edits, learning from feedback. Design the interaction model that turns an agent from a tool you use to a teammate that earns trust over time.\n\n06\n\nThe evals flywheel\nEvery proposal a firm accepts, edits, or rejects is a training signal. Over time we can learn what makes a great proposal for this firm, in this discipline, to this client - and feed that back into the agent. That signal loop, properly built, is the moat. Help us build it.\n\n#J-18808-Ljbffr","datePosted":"2026-10-09T03:44:24.966Z","dateModified":"2026-10-09T03:44:24.966Z","hiringOrganization":{"@type":"Organization","name":"Buoyant","sameAs":"https://jobsearcher.com"},"jobLocation":{"@type":"Place","address":{"@type":"PostalAddress","addressLocality":"Millbrae","addressRegion":"CA","addressCountry":"US"}},"identifier":{"@type":"PropertyValue","name":"JobSearcher","value":"0f454fa78b7b8deda1dcdf1f"},"url":"https://jobsearcher.com/jobs/0f454fa78b7b8deda1dcdf1f"}}