{"id":1266645,"url":"https://alion.io/job/clarus-impact-network-applied-ai-site-reliability-engineer-iii","title":"Applied AI Site Reliability Engineer III","company":{"id":3801525,"name":"Clarus- Impact Network","domain":"clarusadvisers.com","url":"https://alion.io/company/clarus-impact-network","size_band":null,"is_staffing_agency":true,"employer_type":"agency","is_intermediary":false,"listed_via":null,"ats_vendor":null,"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":["Bengaluru, India","Hyderabad, India"],"countries":["IN"],"hiring_countries":[],"hiring_countries_total":0,"salary":null,"salary_estimate":{"min_usd":11500,"max_usd":33000,"period":"year","method":"role_seniority_country_remote_cell","sample_n":26},"experience_years_min":5,"visa_sponsorship":false,"relocation_package":false,"has_equity":false,"technologies":[{"name":".NET","optional":false},{"name":"AI Agents","optional":false},{"name":"Amazon CloudWatch","optional":false},{"name":"AWS","optional":false},{"name":"AWS Bedrock","optional":false},{"name":"Azure","optional":false},{"name":"Azure DevOps","optional":false},{"name":"C#","optional":false},{"name":"Chaos Engineering","optional":false},{"name":"CI/CD","optional":false},{"name":"Datadog","optional":false},{"name":"Docker","optional":false},{"name":"Dynatrace","optional":false},{"name":"FinOps","optional":false},{"name":"GCP","optional":false},{"name":"GitHub","optional":false},{"name":"Grafana","optional":false},{"name":"Incident Management","optional":false},{"name":"Java","optional":false},{"name":"JMeter","optional":false},{"name":"k6","optional":false},{"name":"Kubernetes","optional":false},{"name":"LLM","optional":false},{"name":"LLM Guardrails","optional":false},{"name":"LLMOps","optional":false},{"name":"OpenAI","optional":false},{"name":"OpenTelemetry","optional":false},{"name":"Prometheus","optional":false},{"name":"Python","optional":false},{"name":"SLI/SLO/SLA","optional":false},{"name":"Splunk","optional":false},{"name":"SQL","optional":false},{"name":"Terraform","optional":false},{"name":"Vertex AI","optional":false},{"name":"Langfuse","optional":true},{"name":"LangSmith","optional":true},{"name":"Least Privilege","optional":true},{"name":"MLFlow","optional":true}],"status":"live","first_seen_at":"2026-09-03T09:46:30Z","employer_posted_date":null,"last_verified_at":"2026-09-03T09:46:30Z","board_verified":false,"closed_at":null,"days_open":51,"trust":{"level":"not_scored","repost_count":null,"flags":[],"days_open":51},"description":"About the Role : \n\nWe are looking for an experienced Applied AI Site Reliability Engineer III to join a high-performing Product Engineering team responsible for building and operating reliable, scalable, cloud-native platforms and AI-enabled products.\n\nThe ideal candidate will combine strong SRE/Production Engineering, Cloud, Observability, Performance Engineering, Kubernetes and Infrastructure-as-Code expertise with hands-on experience operating AI/ML and agentic workloads in production.\n\nKey Responsibilities : \n\n- Own reliability, performance, availability and cost outcomes through SLIs, SLOs, SLAs and error budgets.\n\n- Design and operate production-grade observability across metrics, logs and distributed tracing.\n\n- Build dashboards, actionable alerts, runbooks and automated reliability checks.\n\n- Drive production readiness, release gating and operational acceptance of applications and platforms.\n\n- Manage cloud-native infrastructure across AWS, Azure or GCP.\n\n- Develop and maintain infrastructure using Terraform, Kubernetes, Docker and CI/CD.\n\n- Perform performance, load, capacity and resilience testing.\n\n- Implement chaos engineering and failure-testing practices to improve system resilience.\n\n- Participate in incident management, root-cause analysis and blameless postmortems.\n\n- Identify and eliminate operational toil through automation.\n\n- Support and operate AI/ML and agentic workloads in production.\n\n- Address AI-specific reliability challenges including model drift, train/serve skew, output variance, latency and token/GPU cost anomalies.\n\n- Work with engineering, security, risk, architecture and data teams to establish production standards and controls.\n\n- Contribute to MLOps/LLMOps, AI control planes, model/LLM gateways and guardrails from an operability and performance perspective.\n\n- Drive cloud and AI cost optimization / FinOps initiatives.\n\n- Continuously improve reliability, scalability, security and operational efficiency.\n\nRequired Skills & Experience : \n\n- 5+ years of software engineering / SRE / production engineering experience.\n\n- 3+ years working with large-scale, distributed, cloud-native production systems.\n\n- Strong experience with one or more : Python / Go / Bash / Java / C#/.NET, SQL / NoSQL, Kubernetes & Docker, Terraform, CI/CD, GitHub / Azure DevOps.\n\n- Hands-on experience with AWS, Azure or GCP.\n\n- Strong understanding of : SLI / SLO / SLA, Error budgets, Incident management, On-call operations, Production readiness, Capacity planning, Autoscaling, Environment integrity & configuration drift.\n\n- Experience with observability tools such as OpenTelemetry, Prometheus, Grafana, Datadog, Dynatrace, CloudWatch, Azure Monitor, Google Cloud Operations or Splunk.\n\n- Experience with load/performance testing using tools such as JMeter, LoadRunner or k6.\n\n- Exposure to chaos engineering tools such as AWS Fault Injection Simulator or Azure Chaos Studio.\n\n- Experience operating AI/ML or GenAI workloads in production.\n\n- Understanding of MLOps / LLMOps, AI reliability and agentic systems.\n\n- Experience with AI platforms such as Azure OpenAI, AWS Bedrock or Vertex AI is highly desirable.\n\n- Familiarity with MLflow, LangSmith, LangFuse or equivalent AI/agent orchestration platforms.\n\n- Understanding of DevSecOps, SRE, Lean/XP methodologies and secure production practices.\n\n- Knowledge of RBAC, secrets management, least privilege and deployment controls.\n\n- Strong software engineering fundamentals including OOP/OOD, data structures, algorithms, system design and code instrumentation.\n\nWhat We're Looking For : \n\n- Strong hands-on engineering mindset.\n\n- Excellent troubleshooting and problem-solving skills.\n\n- Ability to work across engineering, security and architecture teams.\n\n- Strong understanding of production systems and operational excellence.\n\n- Data-driven approach to reliability and performance improvements.\n\n- Excellent communication and stakeholder-management skills.\n\n- Willingness to continuously learn emerging cloud and AI technologies.\n\nTravel : Up to 10% may be required.\n\nSkills\nDevOps, Site Reliability, Observability Services, Performance Tuning, IAC Terraform, Kubernetes, Native Cloud, Cloud Infrastructure, Log Management Tools, AWS, Google Cloud Platform","description_format":"text","description_chars":4263,"description_truncated":false,"requirements":{"experience_years_min":5,"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":"2026-09-25T22:00:00Z"}],"visa":[],"liveness":{"score":4,"band":"cold","label":"Long shot","p_open":0.4,"p_active":0.298,"p_room":0.35,"age_days":51,"expected_fill_days":23,"reasons":["seen:51","agency","win:tail"],"computed_at":"2026-10-25T05:49:26Z"},"pay":null,"html_url":"https://alion.io/job/clarus-impact-network-applied-ai-site-reliability-engineer-iii","json_url":"https://alion.io/job/clarus-impact-network-applied-ai-site-reliability-engineer-iii.json","meta":{"generated_at":"2026-10-25T06:37:48Z","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":9215,"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":3801525},"rest":"https://alion.io/mcp/rest/get_company?id=3801525"},"human":"https://alion.io/catalog?offer=company.slices&for=job%2Fclarus-impact-network-applied-ai-site-reliability-engineer-iii"},{"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%2Fclarus-impact-network-applied-ai-site-reliability-engineer-iii"},{"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%2Fclarus-impact-network-applied-ai-site-reliability-engineer-iii"},{"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/clarus-impact-network-applied-ai-site-reliability-engineer-iii\", \"note\": \"what you need it for\"}"},"human":"https://alion.io/catalog?offer=company.verify&for=job%2Fclarus-impact-network-applied-ai-site-reliability-engineer-iii"}]}