{"id":1061150,"url":"https://alion.io/job/retool-software-engineer-agent-platform","title":"Software Engineer, Agent Platform","company":{"id":58778,"name":"Retool","domain":"retool.com","url":"https://alion.io/company/retool","size_band":null,"is_staffing_agency":false,"employer_type":"direct","is_intermediary":false,"listed_via":null,"ats_vendor":"Gem","truth_index":{"grade":"A","score":94,"open_postings":22,"ghost_share":0,"stale_share":0.045,"repost_share":0,"time_to_fill_p50_days":131,"computed_at":"2026-10-04T05:45:00Z"}},"role":"Backend","role_family":"Backend","seniority":"senior","employment_type":"full_time","work_mode":"hybrid","remote_scope":null,"remote_scope_basis":null,"remote_working_hours":null,"hiring_geo_confidence":"explicit","locations":["San Francisco, United States"],"countries":["US"],"hiring_countries":[],"hiring_countries_total":0,"salary":{"min":163800,"max":306000,"currency":"USD","period":"year","gross":null,"usd_annual":306000},"salary_estimate":null,"experience_years_min":6,"visa_sponsorship":false,"relocation_package":false,"has_equity":false,"technologies":[{"name":"Human-in-the-Loop","optional":false},{"name":"LLM","optional":false},{"name":"LLM Guardrails","optional":false},{"name":"Node JS","optional":false},{"name":"React.js","optional":false},{"name":"Tool Use","optional":false},{"name":"TypeScript","optional":false},{"name":"AI Agents","optional":true},{"name":"Embeddings","optional":true},{"name":"Fine-tuning","optional":true},{"name":"JavaScript","optional":true},{"name":"Post-training","optional":true},{"name":"RAG","optional":true}],"status":"live","first_seen_at":"2026-09-16T18:14:37Z","employer_posted_date":"2026-09-21","last_verified_at":"2026-10-04T23:25:21Z","board_verified":true,"closed_at":null,"days_open":18,"trust":{"level":"ok","repost_count":0,"flags":[],"days_open":17},"description":"ABOUT RETOOL\nNearly every company in the world runs on custom software for critical operations like tracking performance metrics, handling support workflows, building admin dashboards, and countless processes you might never have thought of. But most companies don't have the resources to properly invest in these tools, leading to a lot of old, clunky internal software, or worse, teams still stuck in manual and spreadsheet workflows.\nAI has changed who gets to build software. The definition of \"developer\" now includes analysts, operators, and domain experts creating solutions directly-and the tools they reach for are multiplying by the week. That's both an opportunity and a challenge: as more people build with more AI tools, the risk of shipping ungoverned software into production grows just as fast.\nAt Retool, we're building the platform that makes all of it safe to ship. Build with any AI tool you want, then deploy into one place that connects to your real business data, enforces enterprise policies automatically, and lets teams create once and reuse everywhere with shared, trusted components. The cost of building software has collapsed. The cost of governing it hasn't-and that's the problem we solve.\nDevelopers and domain experts have already automated over 100 million hours of work on our platform, freeing them to focus on creative problem-solving and strategic work that drives real business value. The people closest to the problem can now build the software to solve it, safely, and within enterprise guardrails.\nLet's build the future together.\nWHY WE’RE LOOKING FOR YOU\nWe’re building AI-native products where model behavior is part of the product, not just an implementation detail. As LLMs become more capable, the bottleneck is no longer access to models-it’s making non-deterministic systems reliable, evaluable, and trustworthy in production.\nWe’re hiring AI Engineers to own that problem end to end. This is not a role for someone who simply integrates AI APIs into features. It’s for engineers who take responsibility for how probabilistic systems behave over time, how quality is measured in the presence of variance, and how capabilities improve without regressing.\nIf model regressions, subtle behavior drift, or edge-case failures keep you up at night-and you enjoy that kind of ownership-we want to talk.\nWHAT YOU’LL DO\nAs an AI Engineer, you’ll own model-driven behavior in production systems, working across product, infrastructure, and evaluation layers. Your work will directly shape what users experience-and how confidently the team can ship. You might:\nOwn the behavior of AI-powered features across multiple product surfaces, including quality, safety, variance, and failure modes\nDesign and evolve prompting, retrieval, routing, and tool-use strategies that embrace non-determinism while bounding its downside\nBuild and maintain evaluation systems that measure model performance using statistical signals, distributions, and trends-not just pass/fail tests\nDetect, diagnose, and resolve non-deterministic failures such as hallucinations, partial correctness, instruction drift, or sensitivity to context changes\nDefine and implement guardrails, fallbacks, and degradation paths that keep systems useful even when models behave unexpectedly\nPartner with product and infra teams to decide when probabilistic behavior is “good enough” to ship-and when it isn’t\nInfluence model selection, model behavior, and tool design to balance quality, cost, latency, and robustness for real user workflows\nYou’ll work across the stack (e.g., TypeScript, Node.js, React), but your leverage won’t come from code volume alone-it will come from shaping runtime behavior with precision, measurement, and intent.\nWHAT THIS ROLE IS (AND IS NOT)\nThis role is:\nAccountable for AI behavior, not just system correctness\nGrounded in evaluation, iteration, and regression prevention under non-determinism\nComfortable designing systems where outputs vary, confidence is probabilistic, and correctness is contextual\nFocused on shipping dependable products on top of imperfect components\nThis role is not:\nAdding LLM calls to existing features and moving on\nTreating models as black boxes with undefined behavior\nShipping AI features without owning their long-term reliability, drift, or user trust\nTHE SKILLSET YOU’LL BRING\n6+ years of professional engineering experience, with ownership over complex systems in production\nDemonstrated experience owning AI/LLM behavior beyond basic integration, including mitigation of variance and failure modes\nComfort reasoning about probabilistic systems and tradeoffs (quality vs. cost, recall vs. precision, speed vs. robustness)\nExperience designing or maintaining evaluation frameworks, golden datasets, regression detection, or human-in-the-loop feedback loops\nStrong product intuition-you care deeply about what “good” looks like even when outputs are non-deterministic\nAbility to operate independently in ambiguous problem spaces and set quality standards others rely on\nStrong opinions, weakly held-you iterate quickly and adjust based on evidence and observed runtime behavior\nBONUS POINTS\nExperience with RAG, agentic systems, or tool-using models in production\nFamiliarity with vector databases, embeddings, or retrieval pipelines\nExposure to fine-tuning, model routing, or post-training techniques\nExperience building shared AI infrastructure used by multiple teams\nHistory of mentoring engineers on designing for non-determinism and evaluation-driven development\nWHO YOU’LL WORK WITH\nYou’ll join a small, senior team focused on advancing AI capabilities across the product. You’ll collaborate closely with product engineers, infra engineers, designers, and PMs-often acting as the final owner of AI behavior and quality before features reach users.\nYour work will set standards that others build on. If you enjoy being the person teams rely on when AI behavior matters most-and certainty is never guaranteed-you’ll thrive here.\nREADY TO BUILD RELIABLE AI SYSTEMS?\nIf you’re excited to move beyond demos and take real ownership of non-deterministic behavior in production-defining quality, preventing regressions, and turning variability into a strength-we’d love to meet you.\nFor candidates based in the United States, the pay range(s) for this role is listed below and represents base salary range for non-commissionable roles or on-target earnings (OTE) for commissionable roles. This salary range may be inclusive of several career levels at Retool and will be narrowed during the interview process based on a number of factors such as (but not limited to), scope and responsibilities, the candidate’s experience and qualifications, and location.\nAdditional compensation in the form(s) of equity and/or commission are dependent on the position offered. Retool provides a comprehensive benefit plan, including medical, dental, vision, and 401(k). Pay and benefits are subject to change at any time, consistent with the terms of any applicable compensation or benefit plans.\nThe base pay range for this role is $163,800 - $306,000 per year.\nRetool offers generous benefits to all employees and hybrid work location. For more information, please visit the benefits and perks section of our careers page!\nRetool is currently set up to employ all roles in the US and specific roles in the UK. To find roles that can be employed in the UK, please refer to our careers page and review the indicated locations.","description_format":"text","description_chars":7477,"description_truncated":false,"requirements":{"experience_years_min":6,"management_years_min":null,"team_size_min":null,"manages_managers":false,"education":null,"security_clearance":false,"languages":[]},"benefits":["Equity","Hybrid work"],"hiring_locations":[{"name":"United States","iso":"US","kind":"country"}],"hiring_excludes":[],"relocation_offered":false,"industries":["Low-Code & No-Code Platforms"],"lifecycle":[{"event":"open","at":"2026-09-19T08:16:17Z"}],"visa":[{"country":"US","licensed_sponsor":true,"evidence":"H-1B filings in 12 months: 8 · green card filings: 6","filings_12m":8,"filings_prev_12m":10,"green_card_filings_12m":6,"median_offered_wage_usd":174643,"route":null,"cap_exempt":false,"checked_at":"2026-10-03T21:08:04+00:00","sources":["US Department of Labor: LCA disclosure data (H-1B, H-1B1, E-3)","US Department of Labor: PERM disclosure data (green cards)"],"filings_for_role_12m":4}],"liveness":{"score":90,"band":"hot","label":"Hiring now","p_open":1,"p_active":0.903,"p_room":1,"age_days":17,"expected_fill_days":131,"reasons":["conf:0","velocity","win:early"],"computed_at":"2026-10-04T05:45:00Z"},"pay":{"stated_usd_annual":306000,"is_top_pay":true},"html_url":"https://alion.io/job/retool-software-engineer-agent-platform","json_url":"https://alion.io/job/retool-software-engineer-agent-platform.json","meta":{"generated_at":"2026-10-05T00:44:46Z","cache_seconds":300,"methodology":"https://alion.io/methodology","terms":"https://alion.io/terms","contact":"https://alion.io/contact","api":"https://alion.io/developers","usage":{"tier":"crawler","counted_by":"address","units_charged":1,"used_today":922,"day_limit":5000,"remaining_today":4078,"minute_limit":60,"resets_at":"2026-10-06T00:00:00Z"}}}