{"id":1065860,"url":"https://alion.io/job/netbrain-ai-engineer-4","title":"AI Engineer","company":{"id":716670,"name":"NetBrain","domain":"netbrain.com","url":"https://alion.io/company/netbrain-2","size_band":null,"is_staffing_agency":false,"employer_type":"direct","is_intermediary":false,"listed_via":null,"ats_vendor":"Greenhouse","truth_index":{"grade":"B","score":77,"open_postings":12,"ghost_share":0,"stale_share":0.917,"repost_share":0,"time_to_fill_p50_days":37,"computed_at":"2026-10-17T05:46:00Z"}},"role":"AI/ML","role_family":"AI/ML","seniority":"senior","employment_type":null,"work_mode":"hybrid","remote_scope":null,"remote_scope_basis":null,"remote_working_hours":null,"hiring_geo_confidence":"structured","locations":["Toronto, Canada"],"countries":["CA"],"hiring_countries":[],"hiring_countries_total":0,"salary":null,"salary_estimate":{"min_usd":90000,"max_usd":162000,"period":"year","method":"role_seniority_country_remote_cell","sample_n":56},"experience_years_min":3,"visa_sponsorship":false,"relocation_package":false,"has_equity":false,"technologies":[{"name":"AutoGen","optional":false},{"name":"DPO","optional":false},{"name":"Fine-tuning","optional":false},{"name":"Function Calling","optional":false},{"name":"GraphRAG","optional":false},{"name":"Hallucination","optional":false},{"name":"Human-in-the-Loop","optional":false},{"name":"Knowledge Graph","optional":false},{"name":"LangChain","optional":false},{"name":"LangGraph","optional":false},{"name":"LlamaIndex","optional":false},{"name":"LLM","optional":false},{"name":"LLM Guardrails","optional":false},{"name":"LoRA","optional":false},{"name":"Machine Learning","optional":false},{"name":"Model Context Protocol","optional":false},{"name":"Post-training","optional":false},{"name":"Python","optional":false},{"name":"RAG","optional":false},{"name":"RLHF","optional":false},{"name":"SFT","optional":false},{"name":"SLI/SLO/SLA","optional":false},{"name":"Structured Outputs","optional":false},{"name":"Tool Use","optional":false},{"name":"Embeddings","optional":true},{"name":"Hybrid Search","optional":true},{"name":"LangSmith","optional":true},{"name":"PEFT","optional":true},{"name":"Reranking","optional":true}],"status":"live","first_seen_at":"2026-09-18T16:07:04Z","employer_posted_date":"2026-09-18","last_verified_at":"2026-10-17T19:48:13Z","board_verified":true,"closed_at":null,"days_open":29,"trust":{"level":"ok","repost_count":null,"flags":[],"days_open":29},"description":"Founded in 2004, NetBrain is the leader in no-code network automation. Its ground-breaking Next-Gen platform provides IT operations teams with the ability to scale their hybrid multi-cloud connected networks by automating the processes associated with Diagnostic Troubleshooting, Outage Prevention and Protected Change Management. Today, over 2,500 of the world’s largest enterprises and managed services providers leverage NetBrain’s platform.\nWhat We Need\nWe’re looking for a Senior AI Engineer to design and build production-grade agent and RAG systems that power intelligent, reliable automation across our platform. This role combines hands-on engineering with system-level thinking-owning everything from architecture and evaluation to scalability, observability, and reliability in production. The ideal candidate thrives in ambiguity, moves quickly from prototype to production, and brings a strong focus on quality, safety, and real-world impact.\nWhat You'll Do\nAgent Platform Architecture\nDesign and implement core capabilities for an enterprise-grade Agent platform, including orchestration patterns such as ReAct, Plan-and-\nExecute, and Supervisor, as well as tool execution, context and memory management, and safety guardrails.\nDesign enterprise-grade Agent execution and governance mechanisms, including Human-in-the-Loop approval workflows, multi-tenant\npermission isolation, policy enforcement, and secure execution controls.\nBuild reusable Agent Skills, standardized tool interfaces, and a scalable tool ecosystem deeply integrated with NetBrain platform\ncapabilities and business workflows.\nLLM and Model Optimization\nDesign and implement LLM post-training strategies, including domain-specific Supervised Fine-Tuning (SFT), DPO/RLHF-based\npreference alignment, and parameter-efficient fine-tuning techniques such as LoRA, to continuously improve model performance in the\nnetwork operations domain.\nBuild an Agent self-learning feedback loop that converts production execution traces, user feedback, and evaluation results into high-\nquality datasets for continuously improving prompts, skills, models, and retrieval strategies.\nAnalyze and optimize LLM behavior across areas such as instruction following, tool calling, structured output generation, contextual\nunderstanding, reasoning stability, and hallucination mitigation.\nEvaluation, Reliability, and Observability\nBuild production-grade LLM and Agent evaluation frameworks and automated regression pipelines, including benchmark datasets,\ndeterministic checks, LLM-as-a-Judge, tool-call validation, retrieval-quality evaluation, and end-to-end task success metrics.\nEstablish release quality gates and hallucination-detection mechanisms for AI features to prevent significant accuracy, reliability, and\nperformance regressions from reaching production.\nBuild comprehensive AI system observability capabilities, including distributed tracing, structured logging, metrics, dashboards, and\nalerting.\nRapidly diagnose and resolve production AI failures, including hallucinations, incorrect tool selection, invalid tool parameters, Agent\nloops, retrieval-quality degradation, structured-output failures, latency regressions, and unexpected model behavior changes.\nProduction Engineering and Technical Execution\nDesign and implement highly reliable backend services for production AI and Agent workloads, including asynchronous and concurrent\nprocessing, retries, timeouts, caching, rate limiting, and fault isolation.\nContinuously optimize latency, throughput, token consumption, and infrastructure cost to meet platform SLA requirements and support\nlarge-scale production workloads.\nIndependently diagnose and resolve complex AI system issues spanning prompts, models, RAG, tools, Agent workflows, backend\nservices, and infrastructure.\nLead technical design for critical modules and system-level capabilities, ensuring solutions align with platform architecture, security\nrequirements, engineering standards, and product requirements.\nDrive technical improvements based on production data, evaluation results, and benchmarks, and collaborate closely with Engineering,\nProduct, QA, and other teams to deliver solutions into production.\nApplied Research and Technical Strategy\nPrototype, benchmark, and productionize emerging technologies such as GraphRAG, Knowledge Graphs, MCP, LLM Post-Training, and\nAgent Self-Learning to improve grounding, multi-hop reasoning, and domain expertise.\nContinuously evaluate Agent frameworks and supporting infrastructure, including LangChain, LangGraph, AutoGen, and LlamaIndex,\nand provide technical recommendations for platform architecture evolution and product technology strategy.\nStay current with developments in LLM and Agent technologies and rapidly translate promising technologies into measurable, testable,\nand production-ready engineering capabilities.\nWhat You Bring\nBachelor's degree or higher in Computer Science, Artificial Intelligence, Electrical Engineering, or a related technical field. Master's or Ph.D.\npreferred; equivalent practical experience will also be considered.\n3+ years of experience in software engineering, machine learning, or applied AI, including 2+ years building, deploying, and operating production-\ngrade LLM or Agent applications. Must have delivered at least one LLM-powered feature end-to-end and owned its ongoing operation and\nimprovement after production launch.\nDeep understanding of Agent architectures and LLM behavioral characteristics, including instruction following, tool-calling behavior, and context\nsensitivity, with hands-on experience building multi-step workflows involving reasoning, tool execution, state management, structured outputs,\nvalidation, and error recovery.\nProven ability to diagnose and resolve production LLM/Agent failures, including hallucinations, incorrect tool calls, retrieval-quality degradation,\nAgent loops, structured-output failures, latency regressions, and regressions introduced by prompt or model changes.\nStrong Python and distributed backend engineering skills, including API and service development, asynchronous and concurrent programming,\nretries, timeouts, caching, rate limiting, testing, logging, and cross-service performance debugging.\nHands-on experience designing evaluation systems for LLM applications, including dataset construction, metric definition, regression testing, and\nrelease quality gates.\nStrong understanding of security risks associated with LLM and Agent applications, including prompt injection, data leakage, unsafe tool\nexecution, permission boundaries, and uncontrolled Agent autonomy.\nAbility to independently design, implement, debug, deploy, and operate complex production systems.\nPreferred Qualifications\nStrong experience with RAG and advanced retrieval systems, including embeddings, vector and hybrid search, reranking, chunking strategies,\ngrounding and citation mechanisms, as well as multi-hop retrieval, Knowledge Graphs, or GraphRAG.\nFamiliarity with Agent frameworks such as LangGraph, LangChain, AutoGen, and LlamaIndex, as well as standardized protocols such as MCP\n(Model Context Protocol) for connecting Agents with external tools and systems. A strong understanding of the underlying architecture is more\nimportant than expertise in any specific framework.Experience designing Agent runtime mechanisms, including Human-in-the-Loop workflows such as risk classification, approval, interruption, pause\n/resume, as well as context management for long-running Agent workflows, including state persistence, history compression, and memory\nsystems.\nExperience with LangSmith or similar LLM observability and evaluation platforms.\nExperience with LLM fine-tuning, including LoRA or other parameter-efficient fine-tuning techniques.\nExperience applying LLM technologies to networking, infrastructure, cybersecurity, observability, or other complex technical domains.\nFluent in both English and Chinese, with strong cross-regional communication and collaboration skills.\nWhat We Offer\nOur comprehensive compensation package is vital in how we recognize our people for the impact they make on us reaching our goals as a company.\nFor this role, the estimated base is CAD $130,000 - CAD $165,000 + Bonus. The actual salary may vary based on a range of factors, including market and individual qualifications objectively assessed during the interview process.\nThe range listed above is a guideline and may be modified. People Experience offers a comprehensive benefits package in addition to cash compensation that includes but is not limited to RRSP and medical/dental coverage. Speak with your Recruiter for more details on our Total Rewards philosophy.\nNetBrain invites all interested and qualified candidates to apply for employment opportunities.\nQualified applicants will receive consideration for employment without regard to race, color, religion, sex, national origin, disability, protected veteran status, or other characteristics protected by law.\nIf you have a disability that prevents or limits your ability to use or access the site, or if you require any other accommodation in the application process due to a disability, you may request a reasonable accommodation. To make a request, please contact our People Team at:  and we will be happy to assist you.\nIn compliance with applicable laws, NetBrain conducts holistic, individual background reviews in support of all hiring decisions.\nIt is unlawful in Massachusetts to require or administer a lie detector test as a condition of employment or continued employment. An employer who violates this law shall be subject to criminal penalties and civil liability.","description_format":"text","description_chars":9688,"description_truncated":false,"requirements":{"experience_years_min":3,"management_years_min":null,"team_size_min":null,"manages_managers":false,"education":{"level":"bachelor","optional":false},"security_clearance":false,"languages":[{"language":"Chinese","level":"All levels","optional":true},{"language":"English","level":"All levels","optional":true}]},"benefits":[],"hiring_locations":[{"name":"Canada","iso":"CA","kind":"country"}],"hiring_excludes":[],"relocation_offered":false,"industries":["IT Service & Asset Management","Enterprise Networks"],"lifecycle":[{"event":"open","at":"2026-09-19T17:18:57Z"}],"visa":[],"liveness":{"score":41,"band":"fade","label":"Fading","p_open":1,"p_active":0.55,"p_room":0.75,"age_days":28,"expected_fill_days":37,"reasons":["conf:2","stale_co","velocity","win:late"],"computed_at":"2026-10-17T05:46:00Z"},"pay":null,"html_url":"https://alion.io/job/netbrain-ai-engineer-4","json_url":"https://alion.io/job/netbrain-ai-engineer-4.json","meta":{"generated_at":"2026-10-17T22:00:25Z","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":6920,"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":716670},"rest":"https://alion.io/mcp/rest/get_company?id=716670"},"human":"https://alion.io/catalog?offer=company.slices&for=job%2Fnetbrain-ai-engineer-4"},{"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%2Fnetbrain-ai-engineer-4"},{"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%2Fnetbrain-ai-engineer-4"},{"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/netbrain-ai-engineer-4\", \"note\": \"what you need it for\"}"},"human":"https://alion.io/catalog?offer=company.verify&for=job%2Fnetbrain-ai-engineer-4"}]}