{"id":784512,"url":"https://alion.io/job/kepler-agentic-systems-engineer","title":"Agentic Systems Engineer","company":{"id":679336,"name":"Kepler","domain":"kepler.ai","url":"https://alion.io/company/kepler-5","size_band":"51-200","is_staffing_agency":false,"employer_type":"direct","is_intermediary":false,"listed_via":null,"ats_vendor":"Ashby","truth_index":{"grade":"B","score":75,"open_postings":7,"ghost_share":0,"stale_share":1,"repost_share":0,"time_to_fill_p50_days":null,"computed_at":"2026-11-03T05:54:40Z"}},"role":"AI/ML","role_family":"AI/ML","seniority":"senior","employment_type":"full_time","work_mode":"on_site","remote_scope":null,"remote_scope_basis":null,"remote_working_hours":null,"hiring_geo_confidence":"structured","locations":["New York, United States"],"countries":["US"],"hiring_countries":[],"hiring_countries_total":0,"salary":{"min":250000,"max":350000,"currency":"USD","period":"year","gross":null,"usd_annual":350000},"salary_estimate":null,"experience_years_min":7,"visa_sponsorship":false,"relocation_package":false,"has_equity":false,"technologies":[{"name":"AI Agents","optional":false},{"name":"CI/CD","optional":false},{"name":"dbt","optional":false},{"name":"ETL/ELT","optional":false},{"name":"Git","optional":false},{"name":"Knowledge Graph","optional":false},{"name":"LLM","optional":false},{"name":"OpenAI","optional":false},{"name":"Rust","optional":false},{"name":"AWS","optional":true},{"name":"Claude","optional":true},{"name":"JavaScript","optional":true},{"name":"PostgreSQL","optional":true},{"name":"React.js","optional":true},{"name":"TypeScript","optional":true}],"status":"live","first_seen_at":"2026-01-21T18:17:03Z","employer_posted_date":"2026-01-21","last_verified_at":"2026-11-03T18:45:27Z","board_verified":true,"closed_at":null,"days_open":286,"trust":{"level":"stale","repost_count":0,"flags":["stale"],"days_open":285},"description":"Introducing Kepler\nThe Problem\nHigh-stakes industries are falling behind on AI adoption. Their workflows can’t afford wrong answers. And AI can’t be trusted to give right ones because of hallucinations. The barrier isn’t that the models aren’t smart enough. It’s that no one can verify what they produce. The fix isn’t a better model, it’s a trust layer: every output traceable, every calculation auditable, every answer reproducible.\nWhat Kepler Is\nKepler is the agent harness - the infrastructure layer that wraps around AI models to make their outputs reliable, traceable, and verifiable. The model is a replaceable component. The harness is the product.\nIn Kepler's architecture, the LLM orchestrates - it decides what data to gather, what to compute, how to structure the output. But every actual data point, every extracted value, every calculation flows through deterministic code pipelines. The LLM never touches the data itself. Every value carries provenance metadata back to its exact source. Every computation is auditable and reproducible. Verification loops cross-check outputs before users ever see them.\nWe started in finance because the stakes are highest and the tolerance for error is zero. We’ve built a finance research product that lets analysts supercharge their workflow: pulling comparables, building models and researching filings. No more double-checking every number AI spits out. Every number tracing back to the source, every time.\nBut the architecture - provenance, deterministic computation, verification - applies anywhere trust in AI output matters: chemicals, legal, healthcare. Models are commoditizing fast. The trust layer is what's missing and the market is massive.\nThe Team\nThe founding team spent a combined 40+ years at Palantir building the type of large-scale data infrastructure that Kepler requires. Our founding engineers led Foundry's core systems - Ontology, Fusion, Workshop, FoundryML, created Palantir's first AI platform and scaled data products at Meta to 1B+ users.\nWe’ve paired this deep technical foundation with a repeat founder profile. Our CEO built and scaled a data company to $15M ARR before successfully selling it. He then became Citadel's first Head of Business Engineering, experiencing first hand the problems we are now solving. We have a team who’ve been on both sides: building systems like this at massive scale and selling it into the buyers who need it most.\nWe’re backed by investors who built the modern AI and data stacks, plus the builders of iconic commercial businesses. This includes founders of OpenAI, Meta AI Research, MotherDuck, dbt Labs and Square as well as PebbleBed, Company Ventures and Mantis VC firms.\nThe Role\nWhat You'll Own\nYou'll build the agentic infrastructure that powers Kepler's AI research platform. You'll work on the foundational systems that make autonomous AI agents reliable at scale: distributed execution frameworks that run thousands of agents in parallel, evaluation systems that ensure agent quality, context management that maximizes agent performance, and the ontology and provenance systems that let us trace every number back to its source.\nThis role is for engineers who want to work at the frontier of AI systems, building the infrastructure that makes agents trustworthy for enterprise-critical decisions. This is our most senior individual contributor role: you build the runtime our agents execute on, the layer the models, workflows, and product all depend on.\nWithin your first 90 days, you will:\nOwn a production agent system end-to-end, from architecture to deployment\n\nBuild and deploy infrastructure that powers real financial research workflows\n\nSee your code enable agents to conduct research at top financial institutions\n\nWhat You'll Do\nBuild agent execution infrastructure: Distributed systems that orchestrate and run massive numbers of agents in parallel with reliability, retry logic, and graceful degradation.\n\nBuild evaluation systems: Frameworks that measure agent quality, catch regressions, and ensure agents perform reliably across diverse research tasks.\n\nOptimize agent performance: Context compression, prompt optimization, model routing, and latency reduction. Make agents faster and smarter.\n\nBuild ontology and provenance systems: The semantic layer that maps concepts to precise definitions and traces every output back to authoritative sources. This is what makes our platform trustworthy.\n\nIntegrate AI into production: Language models powering intelligent research workflows with robust error handling, fallback mechanisms, and cost optimization.\n\nOwn systems end-to-end: Design to production. Services, database optimization, deployment, monitoring.\n\nShip with production excellence: Comprehensive testing, monitoring, deployment pipelines. You own reliability for what you build.\n\nWho You Are\n7+ years building production software. No upper limit, comp scales with experience.\n\nBackend: deep distributed-systems experience. Our backend is Rust, but we don't require Rust experience. We believe strong engineering fundamentals and experience in other languages is what matters.\n\nArchitecture: Experience designing systems that scale and handle complex workflows\n\nAI/ML systems: Experience building with LLMs, agent frameworks, or ML infrastructure\n\nData: Large datasets, ETL pipelines, knowledge graphs or semantic systems a plus\n\nPractices: Git workflows, CI/CD, automated testing, observability\n\nStrong communicator who can discuss technical trade-offs clearly\n\nCurious about the frontier of AI agents and eager to push what's possible\n\nThrives in fast-paced environments with high ownership\n\nDon't check every box? Apply anyway. We prioritize problem-solving ability, systems thinking, and drive to build transformative agentic infrastructure.\nOur Technical Stack\nBackend: Rust - agent orchestration, data extraction, computation pipelines.\n\nFrontend: TypeScript, React - the analyst workspace and verification interfaces.\n\nData: PostgreSQL, plus direct integrations with official data sources.\n\nInfra: AWS.\n\nAI: Model-agnostic by design. We currently use Claude and GPT. The model is the replaceable part.\n\nMentorship & Growth\nYou'll be directly mentored by engineers who built Palantir's core systems. Expect:\nWeekly 1:1s with senior engineers who've built systems at Palantir and Meta scale.\n\nDeep architectural reviews and guidance on system design.\n\nClear growth path toward technical leadership and system ownership.\n\nLearn by building production systems that power real financial research.\n\nWorking at Kepler\nOur Benefits\n100% covered top-of-the-line medical, dental, and vision insurance for employees and their families. HSA maxed by the company to the IRS limit.\n\nAutomatic coverage for life, AD&D, and disability insurance.\n\nDaily lunch in office.\n\nUnlimited PTO policy.\n\nDevelopment environment budget - latest MacBook Pro, multiple monitors, ergonomic setup, and any development tools you need.\n\n\"Build anything\" budget - dedicated funding for whatever tools, libraries, datasets, or infrastructure you need to solve technical challenges, no questions asked.\n\nLearning budget - attend any conference, course, or program that makes you better at what we're building.\n\nOur Operating Principles\nTrust as the Default: People do their best work when confidence is mutual. We show our work, keep our promises, and flag risks before they bite. Trust isn't an aspiration - it's the baseline.\n\nForward-Deployed with Product DNA: We own customer outcomes while building a product company. We don't win if they don't win.\n\nExtreme Ownership: If you notice a problem, you own it by making sure it doesn’t fall through the cracks. Authority comes from initiative, not job titles. Once you step up, you're accountable for the outcome.\n\nProduction-First Engineering: We design for critical workloads from day one. Durable execution, blue/green deploys, automated rollbacks, continuous delivery with end-to-end observability.\n\nCommunicate with Intent: Great work disappears without great communication. We push information to the people who need it, when they need it. Silence is never the safe choice.\n\nEarn it Every Day: Your work speaks for itself. We create an environment where the best idea wins, the strongest work gets recognized, and everyone is held to the same high standard.\n\nKeep Raising the Bar: Great teams compound. Every hire raises the bar, every win gets named, every person gets the tools and runway to grow.\n\nKepler is an Equal Opportunity Employer and prohibits discrimination and harassment of any kind. We are committed to the principle of equal employment opportunity for all employees and to providing employees with a work environment free of discrimination and harassment.","description_format":"text","description_chars":8754,"description_truncated":false,"requirements":{"experience_years_min":7,"management_years_min":null,"team_size_min":null,"manages_managers":false,"education":null,"security_clearance":false,"languages":[]},"benefits":["Apple Macbook","Unlimited PTO","Vision insurance"],"hiring_locations":[],"hiring_excludes":[],"relocation_offered":false,"industries":["AI Safety & Alignment"],"lifecycle":[{"event":"open","at":"2026-09-12T01:29:15Z"}],"visa":[],"liveness":{"score":8,"band":"cold","label":"Long shot","p_open":1,"p_active":0.275,"p_room":0.28,"age_days":285,"expected_fill_days":36,"reasons":["conf:1","win:tail","crowd:"],"computed_at":"2026-11-03T05:54:40Z"},"pay":{"stated_usd_annual":350000,"is_top_pay":true},"html_url":"https://alion.io/job/kepler-agentic-systems-engineer","json_url":"https://alion.io/job/kepler-agentic-systems-engineer.json","meta":{"generated_at":"2026-11-03T23:08:57Z","cache_seconds":300,"methodology":"https://alion.io/methodology","terms":"https://alion.io/terms","contact":"https://alion.io/contact","api":"https://alion.io/developers","about":"Alion is a live layer of people, companies and AI agents: who they are, whether they are real and active right now, what they do and how to work with them, readable by people and by agents and paid per call.","catalog":"https://alion.io/catalog.json","usage":{"tier":"crawler_verified","counted_by":"address","units_charged":1,"used_today":1706,"day_limit":null,"remaining_today":null,"minute_limit":300,"resets_at":"2026-11-04T00:00:00Z"}},"offers":[{"id":"company.slices","title":"One company in depth, by slice","status":"live","price":{"credits":0.02,"usd":0.002,"plus_per_slice":{"credits":0.05,"usd":0.005}},"unit":"per company, plus each slice with data","note":"the employer in depth","call":{"mcp_tool":"get_company","arguments":{"id":679336},"rest":"https://alion.io/mcp/rest/get_company?id=679336"},"human":"https://alion.io/catalog?offer=company.slices&for=job%2Fkepler-agentic-systems-engineer"},{"id":"market.stats","title":"A market slice: pay, demand and time to fill","status":"live","price":{"credits":1,"usd":0.1},"unit":"per slice","note":"pay, demand and time to fill for this role and place","call":{"mcp_tool":"market_stats"},"human":"https://alion.io/catalog?offer=market.stats&for=job%2Fkepler-agentic-systems-engineer"},{"id":"job.search","title":"Open jobs by role, technology, place, pay and visa","status":"live","price":{"credits":0.02,"usd":0.002},"unit":"per posting in a list","note":"similar open postings","call":{"mcp_tool":"search_jobs"},"human":"https://alion.io/catalog?offer=job.search&for=job%2Fkepler-agentic-systems-engineer"},{"id":"company.verify","title":"Is this company real and active right now","status":"pilot","price":null,"unit":"per company","request":{"url":"https://alion.io/catalog/request","method":"POST","body":"{\"offer\": \"company.verify\", \"for\": \"job/kepler-agentic-systems-engineer\", \"note\": \"what you need it for\"}"},"human":"https://alion.io/catalog?offer=company.verify&for=job%2Fkepler-agentic-systems-engineer"}],"agent":{"mcp":"https://alion.io/mcp/jobs","mcp_open":"https://alion.io/mcp/open","next":[{"tool":"get_job","arguments":{"id":784512}},{"tool":"search_jobs","arguments":{"company":"kepler.ai","detail":"compact"}},{"tool":"match_people","arguments":{"job_id":784512},"note":"people open to offers who fit this vacancy"}],"note":"The same data through MCP tools: https://alion.io/mcp/open needs no sign-in (compact searches, postings, people); https://alion.io/mcp with an Alion account has everything. Docs: https://alion.io/developers"}}