{"id":2653300,"url":"https://alion.io/job/primestaff-scroll-to-top-ai-engineers","title":"AI Engineers","company":{"id":242886,"name":"PrimeStaff Scroll To Top","domain":"primestaff.com.sg","url":"https://alion.io/company/prime-staff","size_band":null,"is_staffing_agency":true,"employer_type":"agency","is_intermediary":false,"listed_via":null,"ats_vendor":"Manatal","truth_index":null},"role":"AI/ML","role_family":"AI/ML","seniority":null,"employment_type":null,"work_mode":"on_site","remote_scope":null,"remote_scope_basis":null,"remote_working_hours":null,"hiring_geo_confidence":"structured","locations":["Manila, Philippines"],"countries":["PH"],"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":"A2A","optional":false},{"name":"Agentic Workflows","optional":false},{"name":"AI Agents","optional":false},{"name":"Azure","optional":false},{"name":"Embeddings","optional":false},{"name":"Function Calling","optional":false},{"name":"Hallucination","optional":false},{"name":"LLM","optional":false},{"name":"LLM Guardrails","optional":false},{"name":"Model Context Protocol","optional":false},{"name":"Multi-Agent Systems","optional":false},{"name":"OpenAI","optional":false},{"name":"Prompt Engineering","optional":false},{"name":"Python","optional":false},{"name":"RAG","optional":false},{"name":"Structured Outputs","optional":false}],"status":"live","first_seen_at":"2026-10-15T22:26:46Z","employer_posted_date":"2026-10-15","last_verified_at":"2026-10-25T05:52:11Z","board_verified":true,"closed_at":null,"days_open":9,"trust":{"level":"ok","repost_count":null,"flags":[],"days_open":9},"description":"AI Engineer\nMid (4-7 years)\nSenior (8-12 years)\nRole Overview\nSupport the design, testing, and optimization of prompts and GenAI-driven workflows. Focus on improving output accuracy, structured responses, and supporting document extraction and business automation use cases.\nLead the design, governance, and optimization of enterprise-grade Gen AI and agentic workflows. Architect multi-agent systems that drive measurable automation outcomes, while ensuring reliability, scalability, and responsible AI practices.\nKey Responsibilities\nDesign and refine prompts for LLM-based applications\nCreate structured output formats (JSON, schema-based responses)\nTest and evaluate AI outputs for accuracy and consistency\nSupport development of simple multi-step AI workflows\nAssist in building reusable prompt libraries\nSupport RAG-based document extraction workflows\nDocument AI behaviour patterns and improvement cycles\nWork closely with business teams to refine outputs\nPrompt & AI Workflow Architecture\nDesign advanced prompt engineering frameworks\nDesign and develop prompt chaining and tool-calling workflows\nDevelop structured output enforcement frameworks\nOptimize AI behavior for enterprise use cases\nAgentic Orchestration\nDesign and implement multi-agent orchestration frameworks. \nDesign and implement agentic workflows and orchestration layers\nBuild AI orchestration services integrating multiple agents\nDevelop and manage:\nRAG pipelines\nEmbedding workflows\nReal-time document processing pipelines Define Agent Skills (task-specific capabilities assigned to agents)\nImplement Agent-to-Agent (A2A) communication patterns\nDesign coordination logic across multiple agents\nDefine escalation and fallback mechanisms\nEnterprise AI Integration\nWork with engineering teams to integrate:\nAgent registries\nMCP connectors (Model Context Protocol or contextual connectors)\nKnowledge sources and enterprise systems\nDesign contextual memory strategies\nOptimization & Governance\nImplement hallucination control and guardrails\nDevelop AI evaluation and benchmarking frameworks\nDefine AI best practices and governance standards\nImprove automation KPIs (e.g., STP improvement)\nEnsure explainability and auditability\nEvaluation & Optimization\nDefine and implement AI evaluation frameworks (accuracy, consistency, completeness)\nEstablish feedback loops using user inputs and production data \nIdentify underperforming prompts and drive improvement cycles \nImprove automation KPIs such as Straight-Through Processing\nAnalyze trends (e.g., prompt accuracy degradation, edge cases) and recommend fixes\nLeadership\nMentor junior AI engineers\nCollaborate directly with business stakeholders\nTranslate business requirements into AI agent designs\nDrive AI adoption maturity across functions\nTechnical Requirements\nStrong understanding of LLM fundamentals\nExperience with:\nFew-shot prompting\nStructured prompting\nPrompt chaining (basic level)\nBasic Python knowledge\nFamiliarity with:\nAzure OpenAI or similar LLM platforms\nVector search concepts\nExposure to:\nAI output evaluation methods\nBusiness process automation\nAI & LLM Expertise\nDeep understanding of LLM behavior and limitations\nStrong expertise in:\nPrompt chaining\nTool invocation frameworks\nStructured response validation\nContext window optimization\nAgentic Systems\nHands-on experience with:\nAgent orchestration frameworks\nMulti-agent collaboration models\nAgent Skills modeling\nAgent registries\nAgent-to-Agent (A2A) integration\nFamiliarity with:\nMCP connectors or contextual integration frameworks\nCross-system context injection\nAzure Ecosystem\nStrong familiarity with Azure AI stack: \nAzure OpenAI \nAzure Cognitive Search \nAzure AI Foundry \nUnderstanding of how AI integrates into: \nAzure Functions \nAPI-based workflows\nEnterprise Architecture\nExperience implementing RAG architecture\nExperience with embeddings & vector databases\nStrong understanding of Azure AI ecosystem\nPython proficiency for experimentation and prototyping\nPreferred Qualifications\nExposure to document processing \nBasic understanding of multi-agent systems\nFamiliarity with AI safety and hallucination control concepts\nStrong written communication skills\nOptional: Insurance domain knowledge (Claims/UW)\nExperience deploying agentic AI in production\nExposure to Responsible AI frameworks\nStrong stakeholder management skills\nExperience defining AI governance operating models\nOptional: Insurance domain expertise (Claims, UW workbench)","description_format":"text","description_chars":4439,"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":"2026-10-15T22:26:46Z"}],"visa":[],"liveness":{"score":48,"band":"ok","label":"Likely open","p_open":1,"p_active":0.505,"p_room":0.945,"age_days":9,"expected_fill_days":23,"reasons":["conf:3","agency","velocity","win:mid"],"computed_at":"2026-10-25T05:49:26Z"},"pay":null,"html_url":"https://alion.io/job/primestaff-scroll-to-top-ai-engineers","json_url":"https://alion.io/job/primestaff-scroll-to-top-ai-engineers.json","meta":{"generated_at":"2026-10-25T08:47:25Z","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":12456,"day_limit":null,"remaining_today":null,"minute_limit":300,"resets_at":"2026-10-26T00:00:00Z"}},"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":242886},"rest":"https://alion.io/mcp/rest/get_company?id=242886"},"human":"https://alion.io/catalog?offer=company.slices&for=job%2Fprimestaff-scroll-to-top-ai-engineers"},{"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%2Fprimestaff-scroll-to-top-ai-engineers"},{"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%2Fprimestaff-scroll-to-top-ai-engineers"},{"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/primestaff-scroll-to-top-ai-engineers\", \"note\": \"what you need it for\"}"},"human":"https://alion.io/catalog?offer=company.verify&for=job%2Fprimestaff-scroll-to-top-ai-engineers"}]}