{"id":3977970,"url":"https://alion.io/job/edmo-senior-agentic-ai-architect","title":"Senior Agentic AI Architect","company":{"id":66142,"name":"EDMO","domain":"goedmo.com","url":"https://alion.io/company/edmo","size_band":"51-200","is_staffing_agency":false,"employer_type":"direct","is_intermediary":false,"listed_via":null,"ats_vendor":null,"truth_index":null},"role":"AI/ML","role_family":"AI/ML","seniority":"staff","employment_type":null,"work_mode":"on_site","remote_scope":null,"remote_scope_basis":null,"remote_working_hours":null,"hiring_geo_confidence":"structured","locations":["Pune, India"],"countries":["IN"],"hiring_countries":[],"hiring_countries_total":0,"salary":null,"salary_estimate":null,"experience_years_min":5,"visa_sponsorship":false,"relocation_package":false,"has_equity":false,"technologies":[{"name":"A2A","optional":false},{"name":"AI Agents","optional":false},{"name":"API Gateway","optional":false},{"name":"AutoGen","optional":false},{"name":"AWS","optional":false},{"name":"Azure","optional":false},{"name":"CrewAI","optional":false},{"name":"Docker","optional":false},{"name":"GCP","optional":false},{"name":"Google ADK","optional":false},{"name":"Human-in-the-Loop","optional":false},{"name":"Hybrid Search","optional":false},{"name":"Kubernetes","optional":false},{"name":"LangChain","optional":false},{"name":"LangGraph","optional":false},{"name":"LLM","optional":false},{"name":"Multi-Agent Systems","optional":false},{"name":"Prompt Engineering","optional":false},{"name":"Python","optional":false},{"name":"Quantization","optional":false},{"name":"RAG","optional":false},{"name":"Semantic Search","optional":false},{"name":"SOC 2","optional":false},{"name":"Threat Modeling","optional":false},{"name":"CI/CD","optional":true},{"name":"Claude","optional":true},{"name":"Databricks","optional":true},{"name":"Gemini","optional":true},{"name":"n8n","optional":true},{"name":"OpenAI","optional":true},{"name":"Vertex AI","optional":true},{"name":"Zapier","optional":true}],"status":"live","first_seen_at":"2026-11-09T18:35:35Z","employer_posted_date":null,"last_verified_at":"2026-11-09T18:35:35Z","board_verified":false,"closed_at":null,"days_open":0,"trust":{"level":"not_scored","repost_count":null,"flags":[],"days_open":0},"description":"As the Agentic AI Architect at EDMO, you will own the end-to-end technical design and architecture of our agentic AI systems. You will be the bridge between research-grade AI ideas and production-hardened implementations - defining how LLM pipelines, multi-agent orchestration, memory systems, and tool-use come together into a coherent, scalable platform.\n\nThis is not a research or prototyping role. You will design systems that run at enterprise scale, handle real student interactions, integrate with university SIS/CRM platforms, and meet compliance standards (FERPA, SOC 2). Equally important, you will be able to communicate complex architecture decisions clearly to engineers, product stakeholders, and enterprise clients.\n\nWhat You'll Own:\nDefine the end-to-end agentic AI architecture - LLM orchestration layers, agent coordination mechanisms, memory management, tool-calling patterns, and multi-agent workflows.\nDesign multi-agent orchestration patterns including hierarchical agents, supervisor-worker topologies, plan-and-execute strategies, and agent-to-agent (A2A) communication.\nArchitect RAG (Retrieval-Augmented Generation) pipelines, hybrid search, and knowledge management systems tailored to higher-education content (catalogs, policies, student data).\nEstablish architectural standards for prompt engineering, context-window management, token budgeting, and evaluation frameworks.\nDesign for non-functional requirements: latency targets, throughput, reliability, observability, cost controls, and scaling guardrails.\nBuild production-grade systems with structured error handling, retry logic, circuit breakers, and fallback execution paths.\nDefine DevSecOps architecture and deployment patterns across multi-cloud environments.\nImplement human-in-the-loop (HITL) checkpoints for sensitive decision points within student journeys.\nEstablish monitoring, observability, and audit logging frameworks for compliance, traceability, and agent behavior analysis.\nDesign secure AI architectures - threat modeling, adversarial prompt defenses, and data privacy controls aligned with FERPA and SOC 2.\nProduce clear architecture documentation: reference diagrams, integration patterns, decision records, ADRs, and runbooks for production operations.\nCommunicate architectural trade-offs to both engineering teams and non-technical enterprise clients in a structured, accessible way.\nLead architecture and design reviews, mentoring engineers on agentic patterns and production best practices.\nServe as the technical point of contact for enterprise client integrations - translating institutional requirements into AI system design.\nStay current with the latest agent frameworks (LangGraph, CrewAI, AutoGen, Google ADK), LLM advancements, and inference optimization techniques.\nBuild prototypes and proof-of-concepts to validate architectural approaches before committing to production builds.\nDrive the technology roadmap for EDMO's agentic platform - identifying where autonomous agents can replace manual workflows with measurable ROI.\n\nYou'll Be a Great Fit If You Have:\n5+ years of hands-on software engineering, with 3+ years specifically in production AI/ML systems.\nDemonstrated experience designing and shipping multi-agent AI systems in production (not just prototypes or demos).\nDeep expertise with LLM orchestration frameworks: LangChain, LangGraph (preferred), and/or AutoGen, CrewAI, Google ADK.\nStrong command of Python and backend engineering fundamentals - APIs, microservices, async patterns.\nHands-on experience with RAG architectures, vector databases, and semantic search.\nProficiency with cloud platforms (AWS, GCP, or Azure) and containerized deployments (Docker, Kubernetes).\nAbility to design systems addressing latency, scalability, reliability, and cost simultaneously - not just \"it works on my local machine\".\nExperience with agent memory architectures: episodic, semantic, procedural - and state management in stateful multi-agent graphs.\nFamiliarity with LLM inference optimization - quantization, model routing, caching, context compression.\nUnderstanding of API gateway design, service boundaries, versioning, and governance.\nAbility to produce clear architecture diagrams and technical documentation accessible to both engineers and non-technical stakeholders.\nExperience presenting architecture to enterprise clients or senior leadership.\nTrack record of leading technical design reviews and influencing architecture decisions without direct authority.\n\nNice to Have:\nExperience with voice AI / telephony.\nSalesforce / CRM integration experience.\nHigher education domain knowledge.\nFERPA / SOC 2 compliance experience.\nFamiliarity with n8n or workflow automation tools.\nExperience with Databricks / MongoDB for AI data pipelines.\nGoogle Gemini / Vertex AI experience.\n\nWhat You Won't Be Doing:\nResearch-only, notebook-bound, or demo-focused ML work.\nLow-code/no-code automation tool configuration (Zapier, Make, etc.).\n\"Prompt-only\" AI work without systems thinking.\nArchitecture decks that never get built.\n\nHow We Work:\nTech Stack: Python, LangGraph, LangChain, Google Gemini / Claude / OpenAI (multi-LLM), MongoDB, Databricks, Salesforce integrations.\nDeployment: Production-grade microservices, containerized on cloud with CI/CD pipelines.\nCompliance Environment: FERPA, SOC 2, VPAT - security and privacy are first-class concerns.\nTeam: Small, high-caliber engineering team. Architects write architecture AND contribute to code.\nClients: US-based universities and EdTech platforms at enterprise scale.\n\nWhat Success Looks Like:\nIn 30 days: Full audit of existing agentic system architecture; documented gaps, risks, and improvement areas.\nIn 60 days: Delivered a reference agentic architecture for at least one production agent workflow; established architecture review process with the engineering team.\nIn 6 months: Led architecture for a major platform capability (e.g., multi-agent student advisor, autonomous enrollment workflow); communicated architecture to at least one enterprise client; established observability and evaluation framework for agents in production.\n\nCompensation & Growth:\nLevel: Senior Architect.\nOpportunity: Direct path to VP of AI as EDMO scales.\nImpact: Your architecture decisions shape the AI experience for hundreds of thousands of students at leading US universities.\nThis role sits at the intersection of applied AI research, enterprise product engineering, and client strategy - rare in the market.\nSkills\nAutoGen, CrewAI, Google ADK, LangChain, LangGraph, Python, RAG, Retrieval-Augmented Generation","description_format":"text","description_chars":6584,"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":[]},"benefits":[],"hiring_locations":[],"hiring_excludes":[],"relocation_offered":false,"industries":["E-learning","Document AI"],"lifecycle":[{"event":"open","at":"2026-11-09T18:35:35Z"}],"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":41,"reasons":["seen:0","win:early"],"computed_at":"2026-11-09T20:39:17Z"},"pay":null,"html_url":"https://alion.io/job/edmo-senior-agentic-ai-architect","json_url":"https://alion.io/job/edmo-senior-agentic-ai-architect.json","meta":{"generated_at":"2026-11-09T20:39:17Z","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":8012,"day_limit":null,"remaining_today":null,"minute_limit":300,"resets_at":"2026-11-10T00:00:00Z"}},"offers":[{"id":"company.slices","title":"One company in depth, by slice","status":"live","price":{"credits":0.1,"usd":0.01,"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":66142},"rest":"https://alion.io/mcp/rest/get_company?id=66142"},"human":"https://alion.io/catalog?offer=company.slices&for=job%2Fedmo-senior-agentic-ai-architect"},{"id":"market.stats","title":"A market slice: pay, demand and time to fill","status":"live","price":{"credits":2,"usd":0.2},"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%2Fedmo-senior-agentic-ai-architect"},{"id":"job.search","title":"Open jobs by role, technology, place, pay and visa","status":"live","price":{"credits":0.1,"usd":0.01},"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%2Fedmo-senior-agentic-ai-architect"},{"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/edmo-senior-agentic-ai-architect\", \"note\": \"what you need it for\"}"},"human":"https://alion.io/catalog?offer=company.verify&for=job%2Fedmo-senior-agentic-ai-architect"}],"agent":{"mcp":"https://alion.io/mcp/jobs","mcp_open":"https://alion.io/mcp/open","next":[{"tool":"get_job","arguments":{"id":3977970}},{"tool":"search_jobs","arguments":{"company":"goedmo.com","detail":"compact"}},{"tool":"match_people","arguments":{"job_id":3977970},"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"}}