{"id":1298117,"url":"https://alion.io/job/macrohire-storage-ai-architect","title":"Storage AI Architect","company":{"id":3800331,"name":"MacroHire","domain":"macrohire.in","url":"https://alion.io/company/macrohire","size_band":null,"is_staffing_agency":false,"employer_type":"direct","is_intermediary":false,"listed_via":null,"ats_vendor":null,"truth_index":null},"role":"AI/ML","role_family":"AI/ML","seniority":"staff","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"],"countries":["IN"],"hiring_countries":[],"hiring_countries_total":0,"salary":null,"salary_estimate":{"min_usd":33000,"max_usd":79000,"period":"year","method":"role_seniority_country_remote_cell","sample_n":11},"experience_years_min":10,"visa_sponsorship":false,"relocation_package":false,"has_equity":false,"technologies":[{"name":"AI Agents","optional":false},{"name":"Anomaly Detection","optional":false},{"name":"AWS","optional":false},{"name":"Azure","optional":false},{"name":"Context Engineering","optional":false},{"name":"Embeddings","optional":false},{"name":"Fine-tuning","optional":false},{"name":"Function Calling","optional":false},{"name":"GCP","optional":false},{"name":"GraphRAG","optional":false},{"name":"Hugging Face","optional":false},{"name":"Human-in-the-Loop","optional":false},{"name":"Hybrid Search","optional":false},{"name":"Knowledge Graph","optional":false},{"name":"Kubernetes","optional":false},{"name":"LangChain","optional":false},{"name":"LangGraph","optional":false},{"name":"LLM","optional":false},{"name":"LoRA","optional":false},{"name":"Machine Learning","optional":false},{"name":"Model Context Protocol","optional":false},{"name":"Multi-Agent Systems","optional":false},{"name":"NLP","optional":false},{"name":"PEFT","optional":false},{"name":"PoC Library","optional":false},{"name":"Python","optional":false},{"name":"PyTorch","optional":false},{"name":"Quantization","optional":false},{"name":"RAG","optional":false},{"name":"Reranking","optional":false},{"name":"TensorFlow","optional":false},{"name":"Transformers","optional":false}],"status":"live","first_seen_at":"2026-09-26T08:42:10Z","employer_posted_date":null,"last_verified_at":"2026-09-26T08:42:10Z","board_verified":false,"closed_at":null,"days_open":5,"trust":{"level":"not_scored","repost_count":null,"flags":[],"days_open":5},"description":"Key Responsibilities : \n\n- Architect and develop enterprise-grade Generative AI, LLM and Agentic AI platforms/products, including LLM modules, inference pipelines, model-serving and AI orchestration frameworks.\n\n- Own the LLM lifecycle - model selection, data preparation, fine-tuning, evaluation, deployment, monitoring and performance/cost optimization.\n\n- Design and implement advanced RAG architectures, including data ingestion, embeddings, vector databases, hybrid search, reranking, context engineering, GraphRAG and Agentic RAG.\n\n- Build Agentic AI and multi-agent systems with planning, reasoning, memory, tool/function calling, agent-to-agent communication, MCP integrations and human-in-the-loop workflows.\n\n- Develop intelligent AI agents for storage management, monitoring, troubleshooting, capacity planning, anomaly detection, predictive analytics, RCA and infrastructure automation.\n\n- Apply AI/ML, Deep Learning, NLP and Transformer-based architectures to complex storage, cloud and infrastructure problems.\n\n- Design GenAIOps/MLOps capabilities for model deployment, evaluation, observability, governance and continuous improvement.\n\n- Optimize AI systems for latency, throughput, scalability, GPU utilization, inference performance, token consumption and infrastructure cost.\n\n- Design secure AI architectures addressing prompt injection, data leakage, agent authorization, tool security, AI supply-chain risks and Responsible AI.\n\n- Architect scalable AI platforms across AWS/Azure/GCP and hybrid cloud, leveraging Kubernetes, containers, microservices and distributed systems.\n\n- Integrate AI solutions with storage platforms, APIs, telemetry, logs, metrics, observability and enterprise data sources.\n\n- Drive AI initiatives from research/PoC to enterprise-scale production, collaborating with Product, R&D, Engineering and Architecture teams.\n\nMandatory Skills : \n\n- 10+ years of overall technology experience with strong experience in AI/ML, architecture and product engineering.\n\n- 8+ years of hands-on AI/ML experience with significant GenAI/LLM development experience.\n\n- Proven experience building LLM/GenAI platforms or products, beyond simply consuming AI APIs.\n\n- Strong expertise in LLMs, Transformers, embeddings, RAG, Agentic AI and multi-agent systems.\n\n- Hands-on experience with LLM modules, inference/model serving, fine-tuning, LoRA/PEFT, quantization and model optimization.\n\n- Strong programming skills in Python.\n\n- Hands-on experience with PyTorch/TensorFlow, Hugging Face, LangChain/LangGraph or equivalent frameworks.\n\n- Experience with vector databases, semantic/hybrid search, knowledge graphs and GraphRAG.\n\n- Strong understanding of GenAIOps/MLOps, AI evaluation, observability and governance.\n\n- Strong experience with cloud, Kubernetes, distributed systems, microservices and scalable product architecture.\n\n- Experience in storage, cloud infrastructure, distributed storage, telemetry or observability is highly preferred.\nSkills\nPython, Machine Learning, Generative AI, PyTorch, Tensorflow, LangChain, Kubernetes, Cloud, Storage Infrastructure, Cloud Storage, AI Architecture","description_format":"text","description_chars":3128,"description_truncated":false,"requirements":{"experience_years_min":10,"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":["Professional Services"],"lifecycle":[{"event":"open","at":"2026-09-26T10:00:06Z"}],"liveness":{"score":82,"band":"hot","label":"Hiring now","p_open":1,"p_active":0.823,"p_room":1,"age_days":4,"expected_fill_days":30,"reasons":["seen:4","win:early"],"computed_at":"2026-10-01T05:45:00Z"},"pay":null,"html_url":"https://alion.io/job/macrohire-storage-ai-architect","json_url":"https://alion.io/job/macrohire-storage-ai-architect.json","meta":{"generated_at":"2026-10-02T02:19:17Z","cache_seconds":300,"methodology":"https://alion.io/methodology","terms":"https://alion.io/terms","contact":"https://alion.io/contact","api":"https://alion.io/developers","usage":{"tier":"crawler","counted_by":"address","units_charged":1,"used_today":3105,"day_limit":5000,"remaining_today":1895,"minute_limit":60,"resets_at":"2026-10-03T00:00:00Z"}}}