{"id":26731,"url":"https://alion.io/job/toogeza-ai-video-agent-engineer","title":"AI Video Agent Engineer","company":{"id":7168,"name":"Toogeza","domain":"toogeza.tech","url":"https://alion.io/company/toogeza","size_band":"51-200","is_staffing_agency":true,"employer_type":"agency","is_intermediary":false,"listed_via":null,"ats_vendor":"Ashby","truth_index":{"grade":"A","score":93,"open_postings":44,"ghost_share":0,"stale_share":0.091,"repost_share":0,"time_to_fill_p50_days":126,"computed_at":"2026-10-17T05:46:00Z"}},"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":"inferred","locations":[],"countries":[],"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":"AI Agents","optional":false},{"name":"ComfyUI","optional":false},{"name":"Hugging Face","optional":false},{"name":"JavaScript","optional":false},{"name":"Model Context Protocol","optional":false},{"name":"Multi-Agent Systems","optional":false},{"name":"Multimodal AI","optional":false},{"name":"n8n","optional":false},{"name":"Prompt Engineering","optional":false},{"name":"Python","optional":false},{"name":"RAG","optional":false},{"name":"Structured Outputs","optional":false},{"name":"Tool Use","optional":false},{"name":"Arize Phoenix","optional":true},{"name":"C","optional":true},{"name":"FFmpeg","optional":true},{"name":"LangChain","optional":true},{"name":"LangGraph","optional":true},{"name":"LangSmith","optional":true},{"name":"Promptfoo","optional":true}],"status":"live","first_seen_at":"2026-06-02T11:14:26Z","employer_posted_date":"2026-06-02","last_verified_at":"2026-10-17T13:11:29Z","board_verified":true,"closed_at":null,"days_open":137,"trust":{"level":"ok","repost_count":0,"flags":[],"days_open":136},"description":"We are toogeza, a Ukrainian recruiting company that is focused on hiring talents and building teams for tech startups worldwide. People make a difference in the big game, we may help to find the right ones.\nCurrently, we are looking for AI Video Agent Engineer for Elva.\nLocation: Remote\nJob Type: Full-Time\nOverview:\nWe are building an AI-driven video production system designed as an intelligent multi-agent orchestration layer capable of transforming raw ideas and references into fully structured video content.\nThe system operates as a black-box creative engine for different types of users:\nprofessional video creators\n\ncasual users\n\ncreators of short narrative concepts\n\nUsers provide an idea, references, or media fragments, and the system automatically orchestrates multiple AI agents responsible for analysis, scripting, editing, and production of video content.\nWe are looking for an engineer who can design and implement multi-agent pipelines, orchestrate AI tools, and build intelligent workflows that combine video analysis, storytelling logic, and automated editing.\nThis role sits at the intersection of AI systems architecture, creative tooling, and multimodal content generation.\nResponsibilities:\nAI Agent Architecture\nDesign and implement the architecture of a multi-agent video editing system including agents responsible for:\nvideo analysis\n\nnarrative generation\n\nediting orchestration\n\nproduction and output synthesis\n\nDefine system prompts, behavioral rules, and structured instructions for agents interacting within the pipeline.\nPipeline Orchestration (n8n)\nDevelop and maintain complex orchestration pipelines in n8n, including:\nmulti-agent workflows\n\ntool-calling logic\n\ndynamic routing between tools and models\n\ncontext passing between agents\n\nPipelines must be capable of selecting the most appropriate models, tools, and strategies depending on the task.\nMultimodal Data Processing\nDesign robust pipelines for handling:\nvideo materials\n\nimage assets\n\nuser text prompts\n\nstructured metadata\n\nEnsure proper data transformation and context transfer across the pipeline stages.\nTool & API Integration\nIntegrate both external and internal APIs for multimodal generation and processing, including:\nimage generation\n\nvideo generation\n\nspeech synthesis\n\naudio generation\n\nvideo processing services\n\nRapidly evaluate available APIs and select the best quality tools and models for each task.\nModel Orchestration & Optimization\nTune and optimize model interactions, primarily based on Gemini models, including:\nprompt engineering\n\nstructured outputs\n\ntool-calling workflows\n\nagent collaboration logic\n\nOptimize pipelines for quality, reliability, and execution efficiency.\nFuture Architecture (RAG & Knowledge Systems)\nDesign systems that support:\nvector databases\n\nretrieval-augmented generation (RAG)\n\nmemory and contextual reasoning between agents\n\nExpected Outcomes:\nThe pipeline system should be capable of:\nTaking an idea + references as input\n\nAnalyzing the content\n\nGenerating a coherent narrative structure\n\nSelecting appropriate visual and audio elements\n\nProducing a high-quality, structured video output\n\nRequirements:\nAI Systems & Agent Architecture\nStrong experience building multi-agent systems, including:\nintent and sub-intent modeling\n\nagent orchestration\n\nagent communication and transport layers\n\nsummarization pipelines\n\ncontext passing between agents\n\nWorkflow Orchestration\nHands-on experience with:\nn8n\n\nAgent tool-calling\n\nn8n MCP\n\nExperience designing complex automation pipelines is essential.\nProgramming\nStrong practical coding skills with vibe coding mindset:\nPrimary languages:\nPython\n\nJavaScript\n\nBonus experience:\nComfyUI custom nodes\n\nlightweight APIs (e.g., HuggingFace Spaces or inference endpoints)\n\nMultimodal Tooling Knowledge\nAbility to quickly navigate API documentation and integrate tools for:\nimage generation\n\nvideo generation\n\nspeech synthesis\n\naudio generation\n\nmultimodal analysis\n\nYou should know where and how to obtain the best generation quality for each modality.\nCreative Thinking\nStrong sense of visual rhythm and composition\n\nCreative intuition and storytelling awareness\n\nGood taste in video structure and montage\n\nAbility to evaluate AI-generated output not only by metrics, but also by creative quality and narrative coherence\n\nVideo & Media Processing\nPreferred experience with:\nFFmpeg\n\nvideo processing pipelines\n\nimage processing workflows\n\nNice to Have:\nThe following qualifications are not mandatory, but will significantly strengthen a candidate’s profile during the evaluation process:\nAgentic Frameworks\nDeep understanding of frameworks such as LangGraph and LangChain for building complex cyclic state graphs and stateful agent systems.\nAdvanced RAG & Memory Management\nExperience designing long-term memory systems for agents, including mechanisms for storing and retrieving successful execution patterns or scenarios to improve future performance through experience-based retrieval.\nSelf-Correction & Reflection\nExperience building agents with feedback loops such as self-reflection, self-critique, or strategy correction, enabling them to verify their own actions and adapt execution logic dynamically.\nEvaluation & Observability\nExperience with tools for monitoring, debugging, and evaluating agent chains and prompt behavior, such as LangSmith, Arize Phoenix, or Promptfoo, with the ability to identify logical failures, quality regressions, and orchestration bottlenecks.\nIdeal Candidate:\nThe ideal candidate is someone who naturally operates between engineering and creative production, capable of building systems that automate complex media workflows while preserving narrative coherence and aesthetic quality.\nYou enjoy designing systems where AI agents collaborate to produce meaningful creative outputs.\n\nWhat’s next?\nIf this role sounds like a fit - we’d love to hear from you! Just send over your CV and anything else you’d like us to consider.\nWe’ll review everything within five working days, and if your background matches what we’re looking for, we’ll get in touch to set up a call and get to know each other better.","description_format":"text","description_chars":6123,"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":[]},"benefits":[],"hiring_locations":[],"hiring_excludes":[],"relocation_offered":false,"industries":[],"lifecycle":[{"event":"open","at":"2026-06-02T11:14:26Z"}],"visa":[],"liveness":{"score":17,"band":"cold","label":"Long shot","p_open":1,"p_active":0.394,"p_room":0.44,"age_days":136,"expected_fill_days":126,"reasons":["conf:2","agency","velocity","win:tail","crowd:"],"computed_at":"2026-10-17T05:46:00Z"},"pay":null,"html_url":"https://alion.io/job/toogeza-ai-video-agent-engineer","json_url":"https://alion.io/job/toogeza-ai-video-agent-engineer.json","meta":{"generated_at":"2026-10-17T13:23:56Z","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":17937,"day_limit":null,"remaining_today":null,"minute_limit":300,"resets_at":"2026-10-18T00:00:00Z"}},"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":7168},"rest":"https://alion.io/mcp/rest/get_company?id=7168"},"human":"https://alion.io/catalog?offer=company.slices&for=job%2Ftoogeza-ai-video-agent-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%2Ftoogeza-ai-video-agent-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%2Ftoogeza-ai-video-agent-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/toogeza-ai-video-agent-engineer\", \"note\": \"what you need it for\"}"},"human":"https://alion.io/catalog?offer=company.verify&for=job%2Ftoogeza-ai-video-agent-engineer"}]}