{"id":4246218,"url":"https://alion.io/job/metlife-software-platform-engineer-ii-3","title":"Software Platform Engineer II","company":{"id":450553,"name":"MetLife","domain":"metlife.com","url":"https://alion.io/company/metlife-5","size_band":"501-1000","is_staffing_agency":false,"employer_type":"direct","is_intermediary":false,"listed_via":null,"ats_vendor":"Avature","truth_index":null},"role":"DevOps","role_family":"DevOps","seniority":"middle","employment_type":null,"work_mode":"on_site","remote_scope":null,"remote_scope_basis":null,"remote_working_hours":null,"hiring_geo_confidence":"structured","locations":["Pune, India"],"countries":["IN"],"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":"Azure","optional":false},{"name":"Azure AKS","optional":false},{"name":"Kubernetes","optional":false},{"name":"LangChain","optional":false},{"name":"LangGraph","optional":false},{"name":"LLM","optional":false},{"name":"Apache Kafka","optional":true},{"name":"Azure Cosmos DB","optional":true},{"name":"Azure DevOps","optional":true},{"name":"Bicep","optional":true},{"name":"CI/CD","optional":true},{"name":"Claude","optional":true},{"name":"Docker","optional":true},{"name":"Embeddings","optional":true},{"name":"FAISS","optional":true},{"name":"FastAPI","optional":true},{"name":"Fine-tuning","optional":true},{"name":"Function Calling","optional":true},{"name":"Gemini","optional":true},{"name":"GitHub Actions","optional":true},{"name":"Helm","optional":true},{"name":"JavaScript","optional":true},{"name":"LangSmith","optional":true},{"name":"Milvus","optional":true},{"name":"MLFlow","optional":true},{"name":"Model Context Protocol","optional":true},{"name":"Multi-Agent Systems","optional":true},{"name":"Next.js","optional":true},{"name":"Pinecone","optional":true},{"name":"Platform Engineering","optional":true},{"name":"Prompt Engineering","optional":true},{"name":"Python","optional":true},{"name":"RAG","optional":true},{"name":"React.js","optional":true},{"name":"Redis","optional":true},{"name":"SLI/SLO/SLA","optional":true},{"name":"Structured Outputs","optional":true},{"name":"Terraform","optional":true},{"name":"TypeScript","optional":true}],"status":"live","first_seen_at":"2026-11-13T12:39:16Z","employer_posted_date":"2026-11-13","last_verified_at":"2026-11-13T12:45:12Z","board_verified":true,"closed_at":null,"days_open":0,"trust":{"level":"ok","repost_count":null,"flags":[],"days_open":0},"description":"Job Summary\nWe are seeking a highly skilled Senior AI Backend Engineer to design, build, and productionize backend systems and ML/LLM inference pipelines within cloud-native environments. This role focuses on developing and operating production-grade AI agents powered by frontier models while ensuring scalability, reliability, and operational excellence.The ideal candidate will have strong expertise in backend engineering, model serving, and AI platform development, with hands-on experience in Agentic AI frameworks such as LangGraph and LangChain. You will be responsible for building the orchestration layer around large language models, including tooling, context management, workflow automation, guardrails, and evaluation frameworks.Experience with Azure cloud services, Azure Kubernetes Service (AKS), and cloud-native operations is highly desirable.\nKey Responsibilities:\nAI & Backend Engineering:\nDesign, develop, and maintain scalable backend APIs and microservices using Python, FastAPI, and asynchronous programming patterns.\nBuild and deploy production-ready Agentic AI workflows using LangGraph and LangChain.\nDevelop intelligent agent systems incorporating tool calling, multi-step reasoning, context and memory management, retries, guardrails, and orchestration logic.\nOperate and optimize production AI agents leveraging frontier models such as GPT, Claude, and Gemini, ensuring optimal performance, cost efficiency, and reliability.\nImplement advanced LLM capabilities including Retrieval-Augmented Generation (RAG), vector search, embeddings, prompt engineering, and context management.\nModel Engineering & MLOps:\nPackage, version, deploy, and monitor ML/LLM models for low-latency, batch, and asynchronous inference workloads.\nOptimize model serving infrastructure using frameworks such as MLflow, LangSmith, or equivalent platforms.\nImplement model monitoring, evaluation pipelines, and performance benchmarking processes.\nEvent-Driven Architecture & Integrations:\nBuild resilient event-driven systems utilizing Kafka, Azure Event Hubs, or similar messaging platforms.\nDevelop idempotent consumers, replay mechanisms, and backfill strategies to ensure data consistency and reliability.\nDesign scalable integration frameworks connecting AI services with enterprise systems.\nCloud & Platform Engineering:\nContainerize applications using Docker and deploy workloads on Kubernetes environments, including Azure Kubernetes Service (AKS).\nCreate and manage Kubernetes manifests, Helm charts, and deployment configurations.\nTroubleshoot and optimize containerized workloads, health checks, autoscaling, and resource utilization.\nReliability & Operational Excellence:\nImplement observability solutions including logging, monitoring, metrics, and distributed tracing.\nDefine and track Service Level Objectives (SLOs) and Service Level Indicators (SLIs).\nLead incident response, root-cause analysis, and remediation efforts.\nEnsure secure, scalable, and highly available AI platform operations.\nDevOps & Quality Engineering:\nDevelop automated testing frameworks, CI/CD pipelines, and release automation processes.\nCollaborate with security and platform teams to implement code quality controls and security scanning.\nPromote engineering best practices, test-driven development, and operational excellence.\nCross-Functional Collaboration:\nWork closely with frontend engineering teams using React, Next.js, and TypeScript to deliver end-to-end AI solutions.\nCollaborate with product, data science, and platform engineering teams to deliver scalable AI capabilities.\nRequired Qualifications:\nTechnical Skills:\nStrong proficiency in Python and modern backend frameworks, preferably FastAPI.\nHands-on experience building and operating production AI agents using frontier large language models.\nExpertise in Agentic AI orchestration, including workflow management, tool execution, memory systems, context handling, and guardrails.\nStrong experience with LangGraph and/or LangChain frameworks.\nDeep understanding of model serving, inference optimization, serialization, batching, and monitoring.\nExperience with vector databases and embedding technologies such as FAISS, Milvus, Pinecone, or similar platforms.\nKnowledge of Retrieval-Augmented Generation (RAG) architectures and implementation patterns.\nStrong foundation in distributed systems, concurrency, caching, rate limiting, and reliability engineering.\nExperience with Docker and Kubernetes administration, deployment, and troubleshooting.\nProficiency with CI/CD tools such as Azure DevOps and GitHub Actions.\nExperience working with data pipelines, feature engineering, and data quality management practices.\nWorking knowledge of React and JavaScript/TypeScript for effective collaboration with frontend teams.\nExcellent communication skills and strong written English.\nCloud & Infrastructure Requirements:\nHands-on experience with Microsoft Azure services and Azure Kubernetes Service (AKS).\nExperience with Azure DevOps and cloud-native deployment practices.\nFamiliarity with Redis, Cosmos DB, Azure Container Registry (ACR), and similar managed services.\nPreferred Qualifications:\nExperience with Model Context Protocol (MCP) and AI tool/server integrations.\nKnowledge of load testing, performance tuning, and scalability optimization.\nExperience with model drift detection, explainability tools, MLflow Registry, or LangSmith.\nExposure to multi-agent architectures, fine-tuning techniques, and structured output generation.\nInfrastructure as Code (IaC) experience using Terraform, Bicep, or equivalent technologies.","description_format":"text","description_chars":5587,"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":[{"language":"English","level":"All levels","optional":false}]},"benefits":[],"hiring_locations":[],"hiring_excludes":[],"relocation_offered":false,"industries":["Property & Casualty Insurance","Health Insurance & Benefits","Life Insurance & Annuities"],"lifecycle":[{"event":"open","at":"2026-11-13T12:39:16Z"}],"visa":[],"liveness":{"score":86,"band":"hot","label":"Hiring now","p_open":1,"p_active":0.86,"p_room":1,"age_days":0,"expected_fill_days":15,"reasons":["conf:1","win:early","comp:brand"],"computed_at":"2026-11-13T14:13:59Z"},"pay":null,"html_url":"https://alion.io/job/metlife-software-platform-engineer-ii-3","json_url":"https://alion.io/job/metlife-software-platform-engineer-ii-3.json","meta":{"generated_at":"2026-11-13T14:13:59Z","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":28479,"day_limit":null,"remaining_today":null,"minute_limit":300,"resets_at":"2026-11-14T00:00:00Z"}},"offers":[{"id":"company.slices","title":"One company in depth, by slice","status":"live","price":{"credits":0.1,"usd":0.01,"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":450553},"rest":"https://alion.io/mcp/rest/get_company?id=450553"},"human":"https://alion.io/catalog?offer=company.slices&for=job%2Fmetlife-software-platform-engineer-ii-3"},{"id":"market.stats","title":"A market slice: pay, demand and time to fill","status":"free","price":{"credits":0,"usd":0},"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%2Fmetlife-software-platform-engineer-ii-3"},{"id":"job.search","title":"Open jobs by role, technology, place, pay and visa","status":"live","price":{"credits":0.1,"usd":0.01},"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%2Fmetlife-software-platform-engineer-ii-3"},{"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/metlife-software-platform-engineer-ii-3\", \"note\": \"what you need it for\"}"},"human":"https://alion.io/catalog?offer=company.verify&for=job%2Fmetlife-software-platform-engineer-ii-3"}],"agent":{"mcp":"https://alion.io/mcp/jobs","mcp_open":"https://alion.io/mcp/open","next":[{"tool":"get_job","arguments":{"id":4246218}},{"tool":"search_jobs","arguments":{"company":"metlife.com","detail":"compact"}},{"tool":"match_people","arguments":{"job_id":4246218},"note":"people open to offers who fit this vacancy"}],"note":"The same data through MCP tools: https://alion.io/mcp/open needs no sign-in (compact searches, postings, people); https://alion.io/mcp with an Alion account has everything. Docs: https://alion.io/developers"}}