{"id":188041,"url":"https://alion.io/job/avepoint-ai-engineer-managed-services","title":"AI Engineer (Managed Services)","company":{"id":95172,"name":"AvePoint","domain":"avepoint.com","url":"https://alion.io/company/avepoint-us","size_band":"1001-5000","is_staffing_agency":false,"employer_type":"direct","is_intermediary":false,"listed_via":null,"ats_vendor":"Greenhouse","truth_index":{"grade":"B","score":80,"open_postings":276,"ghost_share":0.257,"stale_share":0,"repost_share":0,"time_to_fill_p50_days":150,"computed_at":"2026-10-17T05:46:00Z"}},"role":"AI/ML","role_family":"AI/ML","seniority":"junior","employment_type":null,"work_mode":"on_site","remote_scope":null,"remote_scope_basis":null,"remote_working_hours":null,"hiring_geo_confidence":"structured","locations":["Singapore"],"countries":["SG"],"hiring_countries":[],"hiring_countries_total":0,"salary":null,"salary_estimate":{"min_usd":38000,"max_usd":78000,"period":"year","method":"role_seniority_country_remote_cell","sample_n":25},"experience_years_min":2,"visa_sponsorship":false,"relocation_package":false,"has_equity":false,"technologies":[{"name":"A/B Testing","optional":false},{"name":"AI Agents","optional":false},{"name":"AutoGen","optional":false},{"name":"AWQ","optional":false},{"name":"Chain-of-Thought","optional":false},{"name":"Cohere SDK","optional":false},{"name":"CrewAI","optional":false},{"name":"DeepEval","optional":false},{"name":"DeepSeek","optional":false},{"name":"FastAPI","optional":false},{"name":"Fine-tuning","optional":false},{"name":"Flask","optional":false},{"name":"Function Calling","optional":false},{"name":"Gemma","optional":false},{"name":"GGUF","optional":false},{"name":"GPTQ","optional":false},{"name":"Haystack","optional":false},{"name":"Hybrid Search","optional":false},{"name":"JAX","optional":false},{"name":"Kubeflow","optional":false},{"name":"Kubernetes","optional":false},{"name":"KV Cache","optional":false},{"name":"LangChain","optional":false},{"name":"LangGraph","optional":false},{"name":"LangSmith","optional":false},{"name":"LiteLLM","optional":false},{"name":"Llama","optional":false},{"name":"llama.cpp","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":"Milvus","optional":false},{"name":"Mistral","optional":false},{"name":"Mixtral","optional":false},{"name":"Model Context Protocol","optional":false},{"name":"Multi-Agent Systems","optional":false},{"name":"Ollama","optional":false},{"name":"OpenAI","optional":false},{"name":"pgvector","optional":false},{"name":"Pinecone","optional":false},{"name":"Pre-training","optional":false},{"name":"Prompt Engineering","optional":false},{"name":"Pydantic","optional":false},{"name":"Python","optional":false},{"name":"PyTorch","optional":false},{"name":"Qdrant","optional":false},{"name":"QLoRA","optional":false},{"name":"Quantization","optional":false},{"name":"Qwen","optional":false},{"name":"RAG","optional":false},{"name":"Ray","optional":false},{"name":"Reranking","optional":false},{"name":"RLAIF","optional":false},{"name":"RLHF","optional":false},{"name":"SGLang","optional":false},{"name":"Speculative Decoding","optional":false},{"name":"Structured Outputs","optional":false},{"name":"TensorFlow","optional":false},{"name":"TensorRT-LLM","optional":false},{"name":"TGI","optional":false},{"name":"Tool Use","optional":false},{"name":"Transformers","optional":false},{"name":"vLLM","optional":false},{"name":"Weaviate","optional":false},{"name":"DSPy","optional":true},{"name":"Model Distillation","optional":true},{"name":"Multimodal AI","optional":true},{"name":"NLP","optional":true},{"name":"PEFT","optional":true},{"name":"PostgreSQL","optional":true},{"name":"TensorRT","optional":true},{"name":"Transfer Learning","optional":true}],"status":"live","first_seen_at":"2026-06-26T05:17:29Z","employer_posted_date":"2026-09-14","last_verified_at":"2026-10-17T10:32:47Z","board_verified":true,"closed_at":null,"days_open":113,"trust":{"level":"ok","repost_count":0,"flags":["company_stale"],"days_open":112},"description":"We are looking for a highly skilled AI Engineer specializing in Large Language Models (LLMs) and Agentic AI. You will architect, build, and deploy production-grade LLM applications - from intelligent knowledge bases and RAG systems to autonomous multi-agent workflows. You will work hands-on with open-source Chinese and international LLMs (DeepSeek, Qwen, Kimi, etc), implementing everything from model deployment and inference optimization to prompt engineering and agent orchestration. This is a builder role for someone who thrives at the intersection of research and engineering.\nKEY RESPONSIBILITIES\nLLM Application Development\nDesign and develop enterprise LLM-powered applications: intelligent Q&A systems, enterprise knowledge base assistants, AI copilots, document analysis tools, and automated customer service agents.\nArchitect and implement end-to-end RAG (Retrieval-Augmented Generation) systems: document parsing and chunking (recursive, semantic, agentic), embedding generation (BGE, M3E, GTE), vector retrieval (dense + sparse hybrid search), reranking (bge-reranker, Cohere Rerank), and response synthesis with source attribution.\nDevelop and optimize Prompt Engineering strategies: chain-of-thought, tree-of-thought, few-shot prompting, structured output parsing (JSON mode / Pydantic), prompt templates (LangChain/LangSmith), and prompt version management.\nKnowledge in harness engineering, context management in ensuring LLM interactions and or AI agents reliable and deterministic.\nAI Agent & Multi-Agent Systems\nDesign and build AI Agent systems using ReAct, Plan-and-Execute, Reflection, and multi-agent collaboration patterns.\nImplement Function Calling and tool-use capabilities, enabling agents to interact with external APIs, databases, and enterprise systems.\nDevelop multi-agent orchestration using LangGraph, AutoGen, CrewAI, and other agent frameworks to solve complex enterprise tasks through agent collaboration.\nDesign MCP (Model Context Protocol) integrations for standardized LLM tool interoperability.\nOpen-Source LLM Deployment & Optimization\nDeploy and optimize latest version of open-source Chinese LLMs: DeepSeek, Qwen, and Kimi for on-premise and private cloud environments.\nImplement model inference optimization: quantization (GGUF/llama.cpp, GPTQ, AWQ, AutoAWQ, FP8/INT8), KV Cache optimization, continuous batching (vLLM, TensorRT-LLM, TGI, SGLang), speculative decoding, and tensor parallelism for high-throughput serving.\nBuild and maintain model serving infrastructure using vLLM, TensorRT-LLM, Text Generation Inference (TGI), Ollama, Xinference, and SGLang; configure GPU resource scheduling with Kubernetes + GPU operators. AI gateway tools for routing, model tracking and load balancing such as TrueFoundry, Kubeflow, LiteLLM or Ray for heavy deep learning.\nModel Fine-Tuning & Customization\nImplement efficient fine-tuning pipelines using LoRA, QLoRA, DoRA, and full-parameter fine-tuning on proprietary domain-specific datasets.\nPrepare and curate instruction-following datasets, RLHF/RLAIF datasets, and evaluation benchmarks for domain adaptation.\nEvaluate fine-tuned models using automated benchmarks and LLM-as-a-Judge methodologies.\nEvaluation & Production Operations\nBuild and maintain LLM evaluation frameworks: LLM-as-a-Judge, RAGAS, DeepEval, ARES, and custom task-specific metrics for continuous quality monitoring.\nImplement production monitoring for LLM systems: output quality tracking, latency/throughput metrics, cost monitoring, drift detection, and guardrail compliance.\nDesign A/B testing frameworks for model comparison and prompt iteration.\nImplement LLM security guardrails: input/output filtering, PII detection, prompt injection defense, content moderation, and safety alignment.\nResearch & Technical Leadership\nTrack frontier AI research and evaluate emerging technologies (new model architectures, training techniques, inference methods) for enterprise adoption.\nContribute to internal knowledge sharing: tech talks, documentation, and best-practice guides on LLM development.\nREQUIRED QUALIFICATIONS\nBachelor's degree or above in Computer Science, Artificial Intelligence, Machine Learning, or related technical field. Master's or PhD in AI/ML preferred.\n2+ years of professional experience in AI/ML engineering with demonstrated production deployment of LLM-based systems at scale.\nDeep understanding of Transformer architecture, attention mechanisms (MHA, GQA, MQA), and LLM pre-training / fine-tuning / inference paradigms.\nExpert proficiency in LLM application frameworks: LangChain, LlamaIndex, Haystack, or equivalent production-grade tools.\nHands-on experience with RAG system development: vector databases (Milvus, ChromaDB, Qdrant, Weaviate, Pinecone, pgvector), embedding models (BGE, M3E, GTE, OpenAI, Cohere), reranking (bge-reranker, Cohere Rerank, cross-encoders), and advanced retrieval techniques (hybrid search, query expansion, HyDE).\nPractical experience deploying and tuning open-source Chinese LLMs: DeepSeek, Qwen, Kimi , or international models (Llama 3.x, Mistral, Mixtral, Gemma, Phi).\nStrong experience with model deployment and serving infrastructure: vLLM, TensorRT-LLM, TGI, Ollama, Xinference, SGLang; GPU resource scheduling (Kubernetes + GPU operators).\nProficiency in model quantization and inference optimization: GGUF (llama.cpp), GPTQ, AWQ, AutoAWQ, FP8/INT8; knowledge of KV Cache optimization and memory-efficient attention (FlashAttention, FlashInfer, PageAttention).\nSolid programming skills in Python; experience with PyTorch, TensorFlow, or JAX; familiarity with FastAPI/Flask for building LLM API services.\nExperience with LLM evaluation methodologies, A/B testing frameworks, and production monitoring of AI systems.\nPREFERRED QUALIFICATIONS\nExperience with agent frameworks: LangGraph, AutoGen, CrewAI, OpenAI Assistants API, and multi-agent orchestration patterns.\nFamiliarity with MCP (Model Context Protocol), OpenAI API specification, and multi-modal LLM capabilities (vision, audio).\nExperience with prompt optimization tools: DSPy, PromptLayer, LangSmith for systematic prompt engineering.\nKnowledge of model distillation and efficient transfer learning from large teacher models to smaller student models.\nContributions to open-source AI projects or publications in NLP/LLM research venues.\nExperience with cloud GPU providers and cost optimization for LLM inference at scale.\nAccess to high-performance GPU computing resources for model development and experimentation.\nAny personal data you share with us during the application process will be processed strictly in compliance with applicable data protection laws and our Privacy Notice.","description_format":"text","description_chars":6673,"description_truncated":false,"requirements":{"experience_years_min":2,"management_years_min":null,"team_size_min":null,"manages_managers":false,"education":{"level":"bachelor","optional":false},"security_clearance":false,"languages":[]},"benefits":[],"hiring_locations":[],"hiring_excludes":[],"relocation_offered":false,"industries":["Data Governance & Catalogs","Security Compliance","Backup & Disaster Recovery"],"lifecycle":[{"event":"open","at":"2026-09-02T01:48:41Z"}],"visa":[],"liveness":{"score":44,"band":"fade","label":"Fading","p_open":1,"p_active":0.731,"p_room":0.6,"age_days":113,"expected_fill_days":150,"reasons":["conf:1","velocity","win:late","crowd:junior,brand"],"computed_at":"2026-10-17T05:46:00Z"},"pay":null,"html_url":"https://alion.io/job/avepoint-ai-engineer-managed-services","json_url":"https://alion.io/job/avepoint-ai-engineer-managed-services.json","meta":{"generated_at":"2026-10-17T10:50:04Z","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":14191,"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":95172},"rest":"https://alion.io/mcp/rest/get_company?id=95172"},"human":"https://alion.io/catalog?offer=company.slices&for=job%2Favepoint-ai-engineer-managed-services"},{"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%2Favepoint-ai-engineer-managed-services"},{"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%2Favepoint-ai-engineer-managed-services"},{"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/avepoint-ai-engineer-managed-services\", \"note\": \"what you need it for\"}"},"human":"https://alion.io/catalog?offer=company.verify&for=job%2Favepoint-ai-engineer-managed-services"}]}