{"id":3871,"date":"2026-10-21T11:24:31","date_gmt":"2026-10-21T04:24:31","guid":{"rendered":"https:\/\/trivita.ai\/?p=3871"},"modified":"2026-10-21T15:58:08","modified_gmt":"2026-10-21T08:58:08","slug":"tuyen-dung-middle-senior-agentic-ai-engineer","status":"publish","type":"post","link":"https:\/\/trivita.ai\/en\/tuyen-dung-middle-senior-agentic-ai-engineer\/","title":{"rendered":"Hiring MIDDLE\/SENIOR AGENTIC AI ENGINEER"},"content":{"rendered":"<p><\/p>\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n<ul class=\"wp-block-list\">\n\n\n\n\n\n\n\n\n\n<\/ul>\n\n\n\n\n\n<ul class=\"wp-block-list\">\n\n\n\n\n\n\n\n<\/ul>\n\n\n\n\n\n<ul class=\"wp-block-list\">\n\n\n\n\n\n\n\n<\/ul>\n\n\n\n\n\n<ul class=\"wp-block-list\">\n\n\n\n\n\n\n\n<\/ul>\n\n\n\n\n\n\n\n<ul class=\"wp-block-list\">\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n<\/ul>\n\n\n\n\n\n\n\n<ul class=\"wp-block-list\">\n\n\n\n<\/ul>\n\n\n\n\n\n<ul class=\"wp-block-list\">\n\n\n\n<\/ul>\n\n\n\n\n\n<ul class=\"wp-block-list\">\n\n\n\n\n\n\n\n\n\n<\/ul>\n\n\n\n\n\n<ul class=\"wp-block-list\">\n\n\n\n<\/ul>\n\n\n\n\n\n<ul class=\"wp-block-list\">\n\n\n\n\n\n\n\n\n\n\n\n\n\n<\/ul>\n\n\n\n\n\n<ul class=\"wp-block-list\">\n\n\n\n<\/ul>\n\n\n\n<p>With the goal of expanding our team to 150\u2013200 employees in 2027, Trivita AI is looking for talented individuals to join us in our next phase of growth.<\/p>\n\n\n\n<p><\/p>\n\n\n\n<p>Trivita AI is hiring Middle\/Senior Agentic AI Engineers with expertise in Python, LLMs, AI agents, RAG, evaluation, and production deployment.<\/p>\n\n\n\n<p>Trivita AI develops AI-powered products and platforms for businesses, including AI assistants, workflow automation agents, knowledge search, and speech recognition. Our systems combine Python backends with commercial and self-hosted LLMs running on GPUs, deployed across Kubernetes, cloud platforms, and on-premise infrastructure.<\/p>\n\n\n\n<p>As a Middle\/Senior Agentic AI Engineer, you will design, develop, and operate end-to-end AI agent systems, covering agent architecture, tool integration, knowledge retrieval, backend services, security, quality evaluation, and production operations.<\/p>\n\n\n\n<p>System success is measured through real-world metrics such as task completion rate, accuracy, latency, and cost per task.<\/p>\n\n\n\n<h2 class=\"wp-block-heading\">Job description<\/h2>\n\n\n\n<h3 class=\"wp-block-heading\"><strong>AI Agent development<\/strong><\/h3>\n\n\n\n<ul class=\"wp-block-list\">\n<li>Design and build AI agents capable of planning, tool calling, and executing multi-step workflows.<\/li>\n\n\n\n<li>Implement checkpointing, durable execution, and human-in-the-loop approval for high-risk actions.<\/li>\n\n\n\n<li>Develop tool integrations using function calling and Model Context Protocol (MCP), ensuring clear schemas, timeouts, and appropriate access controls.<\/li>\n\n\n\n<li>Manage agent context and memory, including conversation summarization, short-term and long-term memory, prompt caching, and token budgets.<\/li>\n\n\n\n<li>Integrate commercial LLMs from OpenAI, Anthropic, and Gemini, as well as self-hosted models through vLLM.<\/li>\n\n\n\n<li>Implement structured outputs, model routing, retries, fallbacks, rate limiting, and cost tracking.<\/li>\n<\/ul>\n\n\n\n<h3 class=\"wp-block-heading\"><strong>Knowledge retrieval and backend engineering<\/strong><\/h3>\n\n\n\n<ul class=\"wp-block-list\">\n<li>Build retrieval pipelines using chunking, indexing, hybrid search, reranking, query rewriting, and metadata filtering.<\/li>\n\n\n\n<li>Apply knowledge graphs and Graph RAG for use cases requiring structured relationships.<\/li>\n\n\n\n<li>Develop Python backends using FastAPI, asynchronous programming, APIs, data models, background jobs, and queues.<\/li>\n\n\n\n<li>Implement real-time streaming through SSE or WebSockets.<\/li>\n\n\n\n<li>Optimize retrieval quality, scalability, and system performance.<\/li>\n<\/ul>\n\n\n\n<h3 class=\"wp-block-heading\"><strong>AI evaluation and security<\/strong><\/h3>\n\n\n\n<ul class=\"wp-block-list\">\n<li>Develop AI evaluation systems using golden datasets, evaluation metrics, LLM-as-judge, and tracing.<\/li>\n\n\n\n<li>Establish automated evaluation workflows to detect quality regressions before releases.<\/li>\n\n\n\n<li>Analyze failure cases, identify root causes, and conduct A\/B tests or ablation studies to validate improvements.<\/li>\n\n\n\n<li>Implement defenses against prompt injection, input\/output validation, personal data protection, and audit logging.<\/li>\n\n\n\n<li>Collaborate with QA teams on labeling guidelines and golden datasets.<\/li>\n<\/ul>\n\n\n\n<h3 class=\"wp-block-heading\"><strong>Production eeployment and operations<\/strong><\/h3>\n\n\n\n<ul class=\"wp-block-list\">\n<li>Package and deploy AI services using Docker, Kubernetes, Helm, and GitOps.<\/li>\n\n\n\n<li>Integrate OpenTelemetry for system tracing and troubleshooting.<\/li>\n\n\n\n<li>Collaborate with DevOps teams on autoscaling and GPU resource management.<\/li>\n\n\n\n<li>Apply AI coding assistants to coding, testing, reviews, and debugging while validating outputs before production deployment.<\/li>\n\n\n\n<li>Research emerging techniques from scientific publications and adopt them when supported by measurable evaluation results.<\/li>\n<\/ul>\n\n\n\n<h2 class=\"wp-block-heading\">Requirements<\/h2>\n\n\n\n<h3 class=\"wp-block-heading\"><strong>Experience and technical skills<\/strong><\/h3>\n\n\n\n<ul class=\"wp-block-list\">\n<li><strong>Middle:<\/strong> 3+ years of software engineering experience with Python as the primary language, including at least 1 year developing LLM-based systems used by real users.<\/li>\n\n\n\n<li><strong>Senior:<\/strong> 5+ years of software engineering experience with Python as the primary language, including at least 2 years developing LLM-based systems used by real users.<\/li>\n\n\n\n<li>Experience deploying at least one AI agent or RAG system to production, with the ability to explain its architecture, failure modes, and evaluation metrics.<\/li>\n\n\n\n<li>Strong Python skills, including async\/await, type hints, Pydantic, and pytest.<\/li>\n\n\n\n<li>Experience operating production backends with FastAPI, PostgreSQL, and Redis.<\/li>\n\n\n\n<li>Strong understanding of embeddings, hybrid search, reranking, and retrieval metrics such as Recall@k, MRR, and nDCG.<\/li>\n\n\n\n<li>Ability to distinguish retrieval errors from generation errors.<\/li>\n\n\n\n<li>Experience developing LLM evaluation systems using datasets, metrics, calibrated LLM-as-judge, and error analysis.<\/li>\n\n\n\n<li>Understanding of tokenization, context windows, sampling, hallucinations, prompt injection, and quality-latency-cost trade-offs.<\/li>\n\n\n\n<li>Proficiency in Docker, Kubernetes, Helm, and at least one major cloud platform (AWS, GCP, or Azure).<\/li>\n\n\n\n<li>Experience using AI coding assistants for development, testing, research, documentation, and workflow automation while complying with data security policies.<\/li>\n\n\n\n<li>Ability to read technical documentation and research papers in English.<\/li>\n<\/ul>\n\n\n\n<h3 class=\"wp-block-heading\"><strong>Level-specific expectations<\/strong><\/h3>\n\n\n\n<p><strong>Middle Agentic AI Engineer<\/strong><\/p>\n\n\n\n<ul class=\"wp-block-list\">\n<li>Build and improve agent\/RAG features within an existing system architecture.<\/li>\n\n\n\n<li>Develop evaluation suites and tests for assigned components.<\/li>\n\n\n\n<li>Use tracing to investigate failures and improve system quality.<\/li>\n<\/ul>\n\n\n\n<p><strong>Senior Agentic AI Engineer<\/strong><\/p>\n\n\n\n<ul class=\"wp-block-list\">\n<li>Design agent architecture, tool integrations, safety layers, and evaluation-gated release workflows.<\/li>\n\n\n\n<li>Make technical decisions balancing quality, latency, and cost.<\/li>\n\n\n\n<li>Provide technical leadership and mentor Middle engineers.<\/li>\n<\/ul>\n\n\n\n<h2 class=\"wp-block-heading\">Technology stack<\/h2>\n\n\n\n<ul class=\"wp-block-list\">\n<li><strong>Programming &amp; Backend:<\/strong> Python, FastAPI, Pydantic, PostgreSQL, Redis.<\/li>\n\n\n\n<li><strong>AI Agent &amp; Integration:<\/strong> LangGraph, MCP, OpenAI, Anthropic, Gemini.<\/li>\n\n\n\n<li><strong>Retrieval &amp; Knowledge:<\/strong> Qdrant, Elasticsearch\/OpenSearch, Neo4j.<\/li>\n\n\n\n<li><strong>LLM Serving:<\/strong> vLLM.<\/li>\n\n\n\n<li><strong>Observability:<\/strong> Langfuse, OpenTelemetry.<\/li>\n\n\n\n<li><strong>Infrastructure:<\/strong> Docker, Kubernetes, Helm, ArgoCD, AWS, GCP, Azure.<\/li>\n<\/ul>\n\n\n\n<h2 class=\"wp-block-heading\">First 6 months expectations<\/h2>\n\n\n\n<ul class=\"wp-block-list\">\n<li>Deploy at least one agent\/RAG feature to production with an evaluation suite and tracing.<\/li>\n\n\n\n<li>Ensure all changes to prompts, models, or retrieval components pass automated evaluation before release.<\/li>\n\n\n\n<li>Deliver at least one measurable improvement in task completion rate, Recall@k, or cost per task, supported by documented results.<\/li>\n<\/ul>\n\n\n\n<h2 class=\"wp-block-heading\">Preferred qualifications<\/h2>\n\n\n\n<ul class=\"wp-block-list\">\n<li>Production experience with knowledge graphs or Graph RAG using Neo4j or equivalent tools.<\/li>\n\n\n\n<li>Experience self-hosting LLMs or speech models on GPUs using vLLM, SGLang, or NVIDIA Triton.<\/li>\n\n\n\n<li>Experience building MCP servers or agent tool platforms.<\/li>\n\n\n\n<li>Familiarity with LangGraph, LlamaIndex, DSPy, Ragas, DeepEval, or Langfuse.<\/li>\n\n\n\n<li>Experience with Qdrant, pgvector, or Elasticsearch\/OpenSearch.<\/li>\n\n\n\n<li>Knowledge of multi-agent systems, long-term agent memory, fine-tuning, or reinforcement learning for agents.<\/li>\n\n\n\n<li>Experience developing agents for healthcare, legal, financial, or sensitive-data environments.<\/li>\n\n\n\n<li>Research publications, open-source contributions, or public technical writing.<\/li>\n<\/ul>\n\n\n\n<h2 class=\"wp-block-heading\">Contact information<\/h2>\n\n\n\n<ul class=\"wp-block-list\">\n<li>Address: No. 01, Street 104, Quarter 3, Binh Trung Ward, Ho Chi Minh City<\/li>\n\n\n\n<li>Phone: 0937519182<\/li>\n\n\n\n<li>Email: <a href=\"mailto:hr@trivita.ai\">hr@trivita.ai<\/a> \/ <a href=\"mailto:le.vu@trivita.ai\">le.vu@trivita.ai<\/a><\/li>\n<\/ul>","protected":false},"excerpt":{"rendered":"<p>With the goal of expanding our team to 150\u2013200 employees in 2027, Trivita AI is looking for talented individuals to join us in our next phase of growth. Trivita AI is hiring Middle\/Senior Agentic AI Engineers with expertise in Python, LLMs, AI agents, RAG, evaluation, and production deployment. Trivita AI develops AI-powered products and platforms &#8230; <a title=\"Hiring MIDDLE\/SENIOR AGENTIC AI ENGINEER\" class=\"read-more\" href=\"https:\/\/trivita.ai\/en\/tuyen-dung-middle-senior-agentic-ai-engineer\/\" aria-label=\"Read more about Tuy\u1ec3n d\u1ee5ng MIDDLE\/SENIOR AGENTIC AI ENGINEER\">Read more<\/a><\/p>","protected":false},"author":1,"featured_media":3864,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[4],"tags":[],"class_list":["post-3871","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-tuyen-dung"],"_links":{"self":[{"href":"https:\/\/trivita.ai\/en\/wp-json\/wp\/v2\/posts\/3871","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/trivita.ai\/en\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/trivita.ai\/en\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/trivita.ai\/en\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/trivita.ai\/en\/wp-json\/wp\/v2\/comments?post=3871"}],"version-history":[{"count":3,"href":"https:\/\/trivita.ai\/en\/wp-json\/wp\/v2\/posts\/3871\/revisions"}],"predecessor-version":[{"id":3879,"href":"https:\/\/trivita.ai\/en\/wp-json\/wp\/v2\/posts\/3871\/revisions\/3879"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/trivita.ai\/en\/wp-json\/wp\/v2\/media\/3864"}],"wp:attachment":[{"href":"https:\/\/trivita.ai\/en\/wp-json\/wp\/v2\/media?parent=3871"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/trivita.ai\/en\/wp-json\/wp\/v2\/categories?post=3871"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/trivita.ai\/en\/wp-json\/wp\/v2\/tags?post=3871"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}