AI Architect Senior (Anekal)

All roles AI / ResearchBangalore, IN BHIVE Workspace, AKR Tech Park (Kudlu Gate) Full-time Hybrid8+ years (4+ in AI/ML architecture) AI Architect Senior Shape the AI architecture behind autonomous data mastering from explainable matching engines and GenAI scoring to the in-product copilot that resolves 95% of user questions at scale. LLM System DesignEntity ResolutionRAGMLOpsMDM / Data Mastering Team AI / Research Location Bangalore, IN BHIVE Workspace, AKR Tech Park (Kudlu Gate) Experience 8+ years (4+ in AI/ML architecture) Tech stack LangChain LlamaIndex OpenAI Anthropic Gemini Open-weight models Pinecone Weaviate pgvector Spark Databricks Snowflake Python TypeScript Node.js AWS (EKS MSK S3 Glue) Apply for this role What youll do 01 Own the end-to-end AI/ML architecture for the matching, stewardship and enrichment engines 02 Define LLM orchestration strategy: RAG, agents, tool-use, fine-tuning and evaluation harnesses 03 Architect explainable entity-resolution pipelines that operate on 10M+ records / day with sub-second latency 04 Design embedding, blocking and reranking strategies for high-recall + high-precision matching on noisy enterprise feeds 05 Lead vendor and model selection across OpenAI, Anthropic, Gemini and open-weight models 06 Design AI copilots embedded in the steward and admin workflows clarifying queries, suggesting rules and explaining match scores 07 Establish evaluation, drift detection and AI-safety standards (hallucination rate, factual accuracy, calibration) 08 Partner with Data Engineering on contracts for streaming + batch ingestion across CRMs, ERPs, PIMs and third-party data feeds 09 Produce Architecture Decision Records and lead technical reviews across engineering pods 10 Mentor senior ICs and align the AI roadmap with product and customer-success stakeholders What were looking for 8+ years in software / ML engineering with 4+ years in AI architecture roles Hands-on experience designing LLM systems RAG, fine-tuning, multi-agent orchestration, structured outputs Deep grasp of entity resolution, blocking, similarity learning and explainable scoring Proven track record designing AI systems running at production scale (10M+ events / day) Robust system-design skills: distributed systems, event-driven architecture, async processing, fault tolerance Proficient in Python; comfort with TypeScript/Node.js for orchestration and API layers Experience with vector databases (Pinecone, Weaviate, pgvector) and semantic search Excellent written communication comfortable producing ADRs and technical narratives Nice to have + Experience in MDM / CDP / entity-resolution products at scale + Familiarity with Salesforce, Databricks, AWS Marketplace integration patterns + Open-source contributions or published research .