{"id":791694,"url":"https://alion.io/job/cobre-senior-ai-product-engineer","title":"Senior AI Product Engineer","company":{"id":184040,"name":"Cobre","domain":"cobre.com","url":"https://alion.io/company/cobre-2","size_band":"11-50","is_staffing_agency":false,"employer_type":"direct","is_intermediary":false,"listed_via":null,"ats_vendor":"Greenhouse","truth_index":null},"role":"Backend","role_family":"Backend","seniority":"senior","employment_type":null,"work_mode":"on_site","remote_scope":null,"remote_scope_basis":null,"remote_working_hours":null,"hiring_geo_confidence":"structured","locations":[],"countries":[],"hiring_countries":[],"hiring_countries_total":0,"salary":null,"salary_estimate":{"min_usd":44000,"max_usd":131000,"period":"year","method":"global_role_cell_scaled_by_country","sample_n":7270},"experience_years_min":5,"visa_sponsorship":false,"relocation_package":false,"has_equity":false,"technologies":[{"name":"Amazon S3","optional":false},{"name":"AWS","optional":false},{"name":"AWS Lambda","optional":false},{"name":"CI/CD","optional":false},{"name":"DynamoDB","optional":false},{"name":"Function Calling","optional":false},{"name":"Go","optional":false},{"name":"Human-in-the-Loop","optional":false},{"name":"Model Context Protocol","optional":false},{"name":"Pipeline as Code","optional":false},{"name":"Vue.js","optional":false},{"name":"AI Agents","optional":true},{"name":"Apache Kafka","optional":true},{"name":"Context Engineering","optional":true},{"name":"JavaScript","optional":true},{"name":"LLM","optional":true},{"name":"Structured Outputs","optional":true},{"name":"TypeScript","optional":true}],"status":"live","first_seen_at":"2026-08-04T20:41:49Z","employer_posted_date":"2026-08-04","last_verified_at":"2026-10-24T11:47:20Z","board_verified":true,"closed_at":null,"days_open":80,"trust":{"level":"ok","repost_count":null,"flags":[],"days_open":80},"description":"What is Cobre, and what do we do?\nCobre is Latin America’s leading instant b2b payments platform. We solve the region’s most complex money movement challenges by building advanced financial infrastructure that enables companies to move money faster, safer, and more efficiently.\nWe enable instant business payments-local or international, direct or via API-all from a single platform.\nBuilt for fintechs, PSPs, banks, and finance teams that demand speed, control, and efficiency. From real-time payments to automated treasury, we turn complex financial processes into simple experiences.\nCobre is the first platform in Colombia to enable companies to pay both banked and unbanked beneficiaries within the same payment cycle and through a single interface.\nWe are building the enterprise payments infrastructure of Latin America!\nThe team you'd lead:\nRisk Products builds the systems that decide who Cobre can do business with and which money movements are allowed to happen: client onboarding and KYB, document collection and verification, sanctions and counterparty screening, real-time transaction decisioning, and the backoffice where compliance analysts do their work.\nTwo things make this team different from a typical backend team:\nWe run the Builder Model. Engineers here own product, design and code end-to-end. You will talk to compliance analysts, read the regulation, write the spec, decide what the screen looks like, build the service behind it, and own the metric that says whether it worked. There is no queue of tickets waiting for you to implement someone else's design.\nWe are AI-native in the product and in how we build it. LLMs do real work in production for us - extracting structured data from incorporation documents and IDs, pre-filling onboarding forms, summarizing evidence for analyst review. And we build with AI: a shared AI toolkit, company-wide MCP servers and custom agents and skills our engineers write for their own workflows.\nWhat we are looking for:\nAn engineer who can take an AI-powered capability from \"this might work\" to \"this runs in production, in a regulated flow, and we can prove it's correct.\"\nWhat would you be doing:\nOwn features end-to-end - from problem framing and product decisions through API design, implementation, rollout, and the metrics that prove the outcome.\nStart from the problem, not from the model - decide where AI genuinely belongs. A deterministic rule that is always right beats a model that is usually right, and in compliance flows that is often the correct trade. We expect you to argue for the boring solution when it is the better one, and to treat cost and latency per decision as product constraints rather than infrastructure footnotes.\nDesign for the model being wrong - confidence thresholds, escalation paths, and human-in-the-loop workflows where the model proposes and an analyst disposes. What the product does with a bad output is a design decision, and it is yours to make.\nDefine correctness before you ship - golden datasets and evaluation suites, a definition of a good result agreed field by field with the people who depend on it, precision and recall measured in production, and explicit thresholds separating full automation from human review. \"It looked right when I tried it\" is not a release criterion.\nTreat prompts, models and thresholds as engineering artifacts - versioned, reviewed, tested and observable, shipped through the same pipeline as code. Not config someone edits in production.\nBuild the deterministic scaffolding around the nondeterministic part - event-driven pipelines, idempotency, retries and DLQs, typed domain models, and an audit trail that holds up to a regulator.\nInstrument before you build - decide the metric and the dashboard up front; correlation IDs that survive every async hop; alerts that mean something.\nDesign for compliance constraints as first-class requirements - PII handling, data retention, traceability, fail-closed defaults.\nWork AI-natively, and own everything you merge - AI assistants, MCP servers and custom agents are part of the daily loop here, and the bar for code produced with them is exactly the bar for code you wrote by hand: understood, tested, and defensible in review. Then contribute the skills, guardrails and patterns that make everyone else faster.\nMentor, and raise the bar around you - pair on the hard problems, review code with substance, help less experienced engineers grow into owning features end-to-end, and write down the decisions that will outlive the ticket. Mentoring is part of the role here, not something you do if there's time left over.\nWhat do you need:\n5+ years building and operating production backend services, with real ownership of what you shipped after it shipped.\nDepth in at least one back-end focused language, and the willingness to learn Go if you don't already know it. Our stack is Go-first, with some Node/TypeScript and Vue 3 in the mix.\nProduction experience with LLM-backed features, not prototypes - structured output, tool use, retrieval, context engineering, evaluation, latency and cost management, and a clear-eyed view of failure modes and fallbacks.\nDistributed systems fundamentals - asynchronous and event-driven processing, at-least-once delivery, idempotency, eventual consistency, and what to do when a downstream provider is down.\nCloud-native AWS development - Lambda, DynamoDB, S3, SQS/SNS - plus containers, IaC and CI/CD as normal parts of your work, not someone else's job.\nArchitectural judgement - hexagonal architecture and DDD in practice: rich domain models, ports and adapters, and the discipline to keep third-party AI SDKs at the edge behind an anti-corruption layer so a model or vendor swap is a one-adapter change.\nTesting discipline - high coverage as a gate rather than an aspiration, table-driven and contract tests, and a real answer for how you test a component that isn't deterministic.\nProduct instinct and directness - you can sit with a compliance analyst, understand why a control exists, and turn that into a spec and a shipped screen.\nA track record of mentoring - you have made other engineers measurably better through pairing, review and onboarding, and you treat that as part of the job.\nProfessional fluency in Spanish - it is our working language, day to day and in design discussions. Working English for technical documentation and reading.\nStrong written and spoken communication, in both.\nNice to have:\nPayments, treasury, banking or fintech background - especially anything touching KYC/KYB, AML, sanctions screening or transaction monitoring.\nExperience with agentic systems: MCP, tool-calling agents, multi-step orchestration, and their evaluation.\nComfort building the frontend for what you ship (we use Vue 3 and an internal design system).\nKafka, schema registries and contract evolution in production.\nWhy this role is worth your time\nYou will own AI capabilities that are load-bearing for how fast Cobre can activate a client and how safely it can move money - in a company where engineers are trusted to decide what to build, not just how to build it.\nIf you're looking for an exciting next step, and this sounds like something that would both challenge and excite you, then this is for you!","description_format":"text","description_chars":7252,"description_truncated":false,"requirements":{"experience_years_min":5,"management_years_min":null,"team_size_min":null,"manages_managers":false,"education":null,"security_clearance":false,"languages":[{"language":"Spanish","level":"Advanced (C1)","optional":false}]},"benefits":[],"hiring_locations":[],"hiring_excludes":[],"relocation_offered":false,"industries":["Financial Software & Embedded Finance","Payment Processing & Gateways"],"lifecycle":[{"event":"open","at":"2026-09-12T03:41:52Z"}],"visa":[],"liveness":{"score":46,"band":"ok","label":"Likely open","p_open":1,"p_active":0.774,"p_room":0.6,"age_days":80,"expected_fill_days":86,"reasons":["conf:2","velocity","win:late","crowd:"],"computed_at":"2026-10-24T06:02:35Z"},"pay":null,"html_url":"https://alion.io/job/cobre-senior-ai-product-engineer","json_url":"https://alion.io/job/cobre-senior-ai-product-engineer.json","meta":{"generated_at":"2026-10-24T15:02:00Z","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":21391,"day_limit":null,"remaining_today":null,"minute_limit":300,"resets_at":"2026-10-25T00:00:00Z"}},"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":184040},"rest":"https://alion.io/mcp/rest/get_company?id=184040"},"human":"https://alion.io/catalog?offer=company.slices&for=job%2Fcobre-senior-ai-product-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%2Fcobre-senior-ai-product-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%2Fcobre-senior-ai-product-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/cobre-senior-ai-product-engineer\", \"note\": \"what you need it for\"}"},"human":"https://alion.io/catalog?offer=company.verify&for=job%2Fcobre-senior-ai-product-engineer"}]}