{"id":3881093,"url":"https://alion.io/job/koltin-ai-engineer","title":"AI Engineer","company":{"id":3782706,"name":"Koltin","domain":"koltin.mx","url":"https://alion.io/company/koltin","size_band":"51-200","is_staffing_agency":false,"employer_type":"direct","is_intermediary":false,"listed_via":null,"ats_vendor":"BambooHR","truth_index":null},"role":"AI/ML","role_family":"AI/ML","seniority":null,"employment_type":"full_time","work_mode":"on_site","remote_scope":null,"remote_scope_basis":null,"remote_working_hours":null,"hiring_geo_confidence":"structured","locations":["Mexico"],"countries":["MX"],"hiring_countries":[],"hiring_countries_total":0,"salary":null,"salary_estimate":null,"experience_years_min":null,"visa_sponsorship":false,"relocation_package":false,"has_equity":false,"technologies":[{"name":"Context Engineering","optional":false},{"name":"Embeddings","optional":false},{"name":"Fine-tuning","optional":false},{"name":"Function Calling","optional":false},{"name":"LLM","optional":false},{"name":"LLM Guardrails","optional":false},{"name":"Model Context Protocol","optional":false},{"name":"Prompt Caching","optional":false},{"name":"RAG","optional":false},{"name":"Structured Outputs","optional":false},{"name":"WhatsApp","optional":false}],"status":"live","first_seen_at":"2026-11-06T18:09:36Z","employer_posted_date":"2026-11-06","last_verified_at":"2026-11-07T07:37:05Z","board_verified":true,"closed_at":null,"days_open":0,"trust":{"level":"ok","repost_count":null,"flags":[],"days_open":0},"description":"About us\nAt Koltin, we’re redesigning the way we care for our moms, dads, and grandparents to help them remain healthy and independent for as long as possible.\nHow do we do it? Through our health memberships, which provide personalized, preventive care to support our members’ long-term well-being.\nWe are the first company in Mexico offering health memberships that include major medical insurance coverage for older adults-up to 84 years old-backed by BBVA Seguros Salud.\nSobre el rol\nBuscamos a nuestro primer(a) Senior Software Engineer - Agents & LLMs. Nuestros miembros nos escriben decenas de miles de veces al mes, muchas veces con miedo, enojo o una historia detrás de la pregunta. Vas a poner agentes en producción para atenderlos, en un dominio donde la respuesta que suena bien y está mal es el peor error posible.\nLo que construyas se vuelve la base de cómo toda la empresa construye con LLMs. Trabajas con producto, data y otros ingenieros, y decides qué construimos, qué compramos y qué ensamblamos.\nGeneralista con una especialidad fuerte (modelo T): te mueves por todo el stack, con inclinación a LLMs y agentes.\nLo que harás\nAgentes en producción.Orquestación, tool calling contra nuestros sistemas y el contexto del miembro armado desde múltiples fuentes, sobre WhatsApp y los canales que vengan.\nLa barra de calidad.Evals sobre casos reales y criterios de aceptación definidos antes de lanzar.\nLa plataforma.Observabilidad de LLMs (trazas, costo, latencia, calidad), evals como infraestructura, acceso a modelos agnóstico de proveedor y versionado de prompts, para que otros equipos no empiecen de cero.\nSeguridad en un entorno regulado.Guardrails, PII, verificación de identidad y human-in-the-loop donde el riesgo lo pide.\nProyectos de punta a punta.Vas por el problema detrás del pedido, lo partes en fases y lo llevas a producción con visibilidad de riesgos y decisiones.\nSubir la vara.ADRs, review, pairing y patrones que otros equipos reusan.\nLo que buscamos\nContratamos por fundamentos, modelos mentales y patrones. El stack se aprende.\n~5+ años de\nHaber llevado LLMs en producción, con al menos un sistema frente a usuarios reales que operaste después del lanzamiento.\nTool calling en serio.Diseñaste las tools y sabes qué hacer cuando el modelo llama la equivocada o con los argumentos equivocados.\nEvals en serio.Datasets de casos reales, LLM-as-judge calibrado contra humanos, regresiones antes de cada cambio de prompt o modelo.\nDatos sensibles en producción: PII, retención, acuerdos de procesamiento con proveedores.\nEspañol nativo o fluido, inglés profesional.\nSuma puntos\nContext engineering: compactación, memoria, context provisioning vía tools.\nRetrieval agéntico y servidores MCP, más allá de RAG sobre embeddings.\nSeguridad de agentes: prompt injection directa e indirecta, permisos mínimos por tool, red-teaming.\nMulti-agente, subagentes y ejecución durable.\nCosto y latencia: prompt caching, routing entre modelos, structured outputs.\nEvals online: shadow mode, A/B entre prompts o modelos, feedback humano que vuelve al dataset.\nWhatsApp, voz, salud o seguros.\nCómo trabajamos\nUsamos IA para todo, y eres dueño(a) de lo que llega a producción.\nSelf-merge por defecto, con CI, tipos y pruebas como bloqueo. Las decisiones de arquitectura viven en ADRs, y ahí enfocamos el review.\nIngeniería se sienta con producto, data y operaciones.\nQué NO es este rol\nInvestigación o fine-tuning: construimos sobre modelos de frontera.\nDemos: lo que cuenta es lo que se sostiene en producción, medido.\nProceso de selección\nRevisión de CV\nEntrevista con People (15 min)\nEntrevista con Producto (45 min)\nEntrevista técnica y live coding con el equipo (1 hora)\nEntrevista Hiring Manager (45 min)\nCierre con Founders (30 min)\nCuidamos el tiempo de las personas: te damos retroalimentación en cada etapa y buscamos cerrar el proceso en pocas semanas.","description_format":"text","description_chars":3874,"description_truncated":false,"requirements":{"experience_years_min":null,"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":["Health insurance","Insurance coverage"],"hiring_locations":[],"hiring_excludes":[],"relocation_offered":false,"industries":["Senior Living & Assisted Living","Health Insurance & Benefits"],"lifecycle":[{"event":"open","at":"2026-11-06T18:09:36Z"}],"visa":[],"liveness":{"score":86,"band":"hot","label":"Hiring now","p_open":1,"p_active":0.86,"p_room":1,"age_days":0,"expected_fill_days":16,"reasons":["conf:2","win:early"],"computed_at":"2026-11-07T05:47:08Z"},"pay":null,"html_url":"https://alion.io/job/koltin-ai-engineer","json_url":"https://alion.io/job/koltin-ai-engineer.json","meta":{"generated_at":"2026-11-07T10:57:51Z","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":10535,"day_limit":null,"remaining_today":null,"minute_limit":300,"resets_at":"2026-11-08T00:00:00Z"}},"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":3782706},"rest":"https://alion.io/mcp/rest/get_company?id=3782706"},"human":"https://alion.io/catalog?offer=company.slices&for=job%2Fkoltin-ai-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%2Fkoltin-ai-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%2Fkoltin-ai-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/koltin-ai-engineer\", \"note\": \"what you need it for\"}"},"human":"https://alion.io/catalog?offer=company.verify&for=job%2Fkoltin-ai-engineer"}],"agent":{"mcp":"https://alion.io/mcp/jobs","mcp_open":"https://alion.io/mcp/open","next":[{"tool":"get_job","arguments":{"id":3881093}},{"tool":"search_jobs","arguments":{"company":"koltin.mx","detail":"compact"}},{"tool":"match_people","arguments":{"job_id":3881093},"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"}}