{"id":1498643,"url":"https://alion.io/job/johnson-controls-tech-lead-data-science","title":"Tech Lead - Data Science","company":{"id":448321,"name":"Johnson Controls","domain":"johnsoncontrols.com","url":"https://alion.io/company/johnsoncontrols-3","size_band":"5000+","is_staffing_agency":false,"employer_type":"direct","is_intermediary":false,"listed_via":null,"ats_vendor":"Workday","truth_index":{"grade":"A","score":88,"open_postings":712,"ghost_share":0.001,"stale_share":0.483,"repost_share":0.008,"time_to_fill_p50_days":24,"computed_at":"2026-10-01T05:45:00Z"}},"role":"Leadership","role_family":"Leadership","seniority":"lead","employment_type":"full_time","work_mode":"hybrid","remote_scope":null,"remote_scope_basis":null,"remote_working_hours":null,"hiring_geo_confidence":"structured","locations":["Mumbai, India"],"countries":["IN"],"hiring_countries":[],"hiring_countries_total":0,"salary":null,"salary_estimate":{"min_usd":22000,"max_usd":58000,"period":"year","method":"role_seniority_country_remote_cell","sample_n":22},"experience_years_min":8,"visa_sponsorship":false,"relocation_package":false,"has_equity":false,"technologies":[{"name":"A/B Testing","optional":false},{"name":"Agentic Workflows","optional":false},{"name":"AI Agents","optional":false},{"name":"AutoGen","optional":false},{"name":"Azure","optional":false},{"name":"Azure Data Factory","optional":false},{"name":"Azure DevOps","optional":false},{"name":"CI/CD","optional":false},{"name":"CrewAI","optional":false},{"name":"Databricks","optional":false},{"name":"Embeddings","optional":false},{"name":"FAISS","optional":false},{"name":"FastAPI","optional":false},{"name":"Function Calling","optional":false},{"name":"GitHub Actions","optional":false},{"name":"Hallucination","optional":false},{"name":"Human-in-the-Loop","optional":false},{"name":"LangChain","optional":false},{"name":"LangGraph","optional":false},{"name":"LangSmith","optional":false},{"name":"LLM","optional":false},{"name":"LLM Guardrails","optional":false},{"name":"LLMOps","optional":false},{"name":"LoRA","optional":false},{"name":"MLFlow","optional":false},{"name":"Model Context Protocol","optional":false},{"name":"Multi-Agent Systems","optional":false},{"name":"NLP","optional":false},{"name":"NumPy","optional":false},{"name":"OpenAI","optional":false},{"name":"OpenTelemetry","optional":false},{"name":"Pandas","optional":false},{"name":"PEFT","optional":false},{"name":"pgvector","optional":false},{"name":"Pinecone","optional":false},{"name":"Prompt Engineering","optional":false},{"name":"Python","optional":false},{"name":"PyTorch","optional":false},{"name":"Qdrant","optional":false},{"name":"RAG","optional":false},{"name":"Scikit-learn","optional":false},{"name":"Semantic Kernel","optional":false},{"name":"SQL","optional":false},{"name":"Structured Outputs","optional":false},{"name":"TensorFlow","optional":false},{"name":"Tool Use","optional":false},{"name":"Weaviate","optional":false},{"name":"Anthropic","optional":true},{"name":"Arize Phoenix","optional":true},{"name":"Azure AKS","optional":true},{"name":"Azure Cosmos DB","optional":true},{"name":"Claude","optional":true},{"name":"Docker","optional":true},{"name":"Fine-tuning","optional":true},{"name":"GPT-4","optional":true},{"name":"GraphRAG","optional":true},{"name":"Hugging Face","optional":true},{"name":"Knowledge Graph","optional":true},{"name":"Kubernetes","optional":true},{"name":"Langfuse","optional":true},{"name":"Llama","optional":true},{"name":"Mistral","optional":true},{"name":"OpenAI Agents SDK","optional":true},{"name":"PostgreSQL","optional":true},{"name":"Power BI","optional":true},{"name":"pySpark","optional":true},{"name":"QLoRA","optional":true},{"name":"Spark","optional":true},{"name":"Transformers","optional":true},{"name":"vLLM","optional":true},{"name":"XGBoost","optional":true}],"status":"live","first_seen_at":"2026-09-29T00:00:00Z","employer_posted_date":"2026-09-29","last_verified_at":"2026-10-01T09:25:34Z","board_verified":true,"closed_at":null,"days_open":3,"trust":{"level":"ok","repost_count":null,"flags":[],"days_open":3},"description":"About the Role\nWe are hiring a Tech Lead -Data Scientist to play a key role in building our Agentic AI Platform - a system of autonomous, tool-using AI agents that plan, reason, and execute complex business workflows end-to-end. The ideal candidate combines strong ML fundamentals with hands-on experience in LLM-based application development, agent orchestration frameworks, and Microsoft Azure cloud services. You will architect and ship production-grade agentic solutions, mentor junior team members, and set technical direction for GenAI initiatives across the organization.\nExperience Range= 8 to 12 yrs\nKey Responsibilities\nDesign, build, and productionize multi-agent systems - including planning, tool calling / function calling, memory, and orchestration - using frameworks such as LangGraph, AutoGen, CrewAI, or Semantic Kernel.\nDevelop RAG pipelines end-to-end: document ingestion, chunking strategies, embeddings, vector search (Azure AI Search / FAISS / pgvector), re-ranking, and grounding for agent knowledge.\nIntegrate agents with enterprise systems and APIs via tool/function calling and Model Context Protocol (MCP) or similar connector patterns.\nBuild and maintain LLM evaluation frameworks for agentic workflows - task-completion metrics, hallucination detection, trajectory analysis, LLM-as-judge pipelines, and A/B testing.\nImplement guardrails, safety, and governance for agents: prompt-injection defense, content filtering, role-based tool permissions, human-in-the-loop checkpoints, and audit logging.\nFine-tune and optimize LLMs where needed (LoRA/PEFT, prompt optimization, model routing, latency/cost trade-offs) on Azure OpenAI / Azure AI Foundry.\nDesign, build, and evaluate classical ML models (classification, regression, forecasting, NLP) where they complement agentic workflows.\nOwn LLMOps/MLOps for the platform: experiment tracking, prompt versioning, CI/CD, observability and tracing (LangSmith, Azure Monitor, OpenTelemetry), drift monitoring, and retraining strategies.\nCollaborate with data engineers on data quality, availability, and governance across Azure Data Lake, Databricks, and Synapse Analytics.\nTranslate ambiguous business problems into agentic AI solutions; present architecture decisions and results to senior stakeholders.\nMentor junior data scientists, lead code/design reviews, and champion engineering best practices.\nRequired Skills & Qualifications\nBachelor's or Master's degree in Computer Science, Data Science, Engineering, Mathematics, or a related field.\n8-10 years of professional experience in data science / ML, with at least 3 years building LLM or GenAI applications in production.\nHands-on experience with agentic frameworks: LangChain/LangGraph, AutoGen, CrewAI, Semantic Kernel, or equivalent (at least one in production).\nStrong understanding of LLM application patterns: prompt engineering, function/tool calling, structured outputs, RAG, agent memory, and multi-agent orchestration.\nExpert-level Python (pandas, NumPy, scikit-learn, async programming, API development with FastAPI).\nHands-on experience with Azure services: Azure OpenAI / AI Foundry, Azure ML, Azure AI Search, Azure Databricks, Azure Data Factory, or Synapse.\nExperience with vector databases and embeddings (Azure AI Search, Pinecone, Weaviate, Qdrant, FAISS, or pgvector).\nSolid grounding in classical ML: supervised/unsupervised learning, model evaluation, and hyperparameter tuning; experience with TensorFlow or PyTorch.\nStrong SQL skills and experience working with large-scale data.\nProven MLOps/LLMOps experience: MLflow, prompt/model versioning, CI/CD (Azure DevOps or GitHub Actions), and production monitoring.\nAbility to evaluate and mitigate LLM-specific risks: hallucination, prompt injection, data leakage, and cost/latency constraints.\nGood to Have\nExperience with Model Context Protocol (MCP), OpenAI Assistants/Agents SDK, or Anthropic tool-use APIs.\nMicrosoft certifications: AI-102 (Azure AI Engineer), DP-100 (Azure Data Scientist Associate).\nExperience fine-tuning open-source LLMs (Llama, Mistral, Phi) using LoRA/QLoRA and serving via vLLM or Azure ML endpoints.\nFamiliarity with observability/tracing for agents: LangSmith, Langfuse, Arize Phoenix, or OpenTelemetry.\nKnowledge of containerization and deployment: Docker, Kubernetes (AKS), Azure Container Apps.\nBig data experience with Apache Spark (PySpark) via Azure Databricks.\nExperience with knowledge graphs, graph RAG, or semantic layers for agent grounding.\nContributions to open-source GenAI/agentic projects or published technical content.\nTechnical Stack\nCategory\nTools & Technologies\nLanguages\nPython, SQL\nAgentic & GenAI\nLangGraph, LangChain, AutoGen, CrewAI, Semantic Kernel, MCP, Azure OpenAI (GPT-4o), Anthropic Claude\nRAG & Vector Search\nAzure AI Search, FAISS, Qdrant, pgvector, Hugging Face embeddings\nML/AI Frameworks\nscikit-learn, XGBoost, PyTorch, TensorFlow, Hugging Face Transformers\nCloud Platform\nMicrosoft Azure (AI Foundry, Azure ML, Databricks, Data Factory, Synapse)\nLLMOps / MLOps\nMLflow, LangSmith/Langfuse, Azure DevOps, GitHub Actions, Docker, AKS\nAPIs & Serving\nFastAPI, Azure Functions, Azure Container Apps\nData & BI Tools\nPower BI, Pandas, PySpark, Jupyter\nStorage & DB\nAzure Blob Storage, Azure Data Lake, SQL Server, Cosmos DB\nWhat We Offer\nCompetitive salary and performance-based incentives.\nOpportunity to architect a greenfield agentic AI platform from the ground up.\nAzure and AI certification sponsorship plus a continuous learning budget.\nTechnical leadership pathway and mentorship opportunities.\nAccess to cutting-edge GenAI tooling, compute, and cross-domain AI projects.\nFlexible hybrid working model and collaborative culture.","description_format":"text","description_chars":5697,"description_truncated":false,"requirements":{"experience_years_min":8,"management_years_min":null,"team_size_min":null,"manages_managers":false,"education":{"level":"bachelor","optional":false},"security_clearance":false,"languages":[]},"benefits":["Continuous learning","Hybrid work"],"hiring_locations":[{"name":"India","iso":"IN","kind":"country"}],"hiring_excludes":[],"relocation_offered":false,"industries":["Energy & Utilities","Government","Energy Efficiency","Smart City"],"lifecycle":[{"event":"open","at":"2026-09-30T03:02:09Z"}],"liveness":{"score":90,"band":"hot","label":"Hiring now","p_open":1,"p_active":0.903,"p_room":1,"age_days":2,"expected_fill_days":24,"reasons":["conf:6","velocity","win:early","comp:brand"],"computed_at":"2026-10-01T05:45:00Z"},"pay":null,"html_url":"https://alion.io/job/johnson-controls-tech-lead-data-science","json_url":"https://alion.io/job/johnson-controls-tech-lead-data-science.json","meta":{"generated_at":"2026-10-02T02:29:30Z","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":3342,"day_limit":5000,"remaining_today":1658,"minute_limit":60,"resets_at":"2026-10-03T00:00:00Z"}}}