Jun 2026 – PresentFull-timeBangalore, India
Analyst — AI & Agent Systems
Designing agentic memory architectures and building agent systems for operations and process intelligence.
- Designing agentic memory architectures that let AI agents retain and recall operational context across multi-step workflows.
- Building agent systems for operations and process intelligence — automating discovery, decision support, and execution monitoring.
- Owning end-to-end delivery: agent orchestration (LangGraph/LiteLLM), backend APIs, evaluation pipelines, and production deployment.
futurestandard.com ↗Jun 2025 – May 2026Full-timeBangalore, India
AI and Fullstack Engineer
Built ComplianceOS end-to-end: compliance automation workflows + agentic analysis over large regulatory corpora (DB → backend → cloud → LLM pipelines).
- Built ComplianceOS end-to-end (DB → backend → cloud → LLM pipelines), cutting BFSI compliance effort by 1,500+ hours/year; AI features contributed to $800K+ ARR growth.
- Owned end-to-end design and migration of a custom RBAC engine (V1→V5) — expression DSL compilation, field-level restrictions, and async context resolution for multi-tenant row-level access over regulatory documents.
- Diagnosed and resolved a production OOMKill on a live document parser; root-caused full-document rasterization holding ~4.9 GB RAM, batched processing cut peak memory by 93%, verified and deployed same day.
- Eliminated N+1 query patterns across high-traffic service paths via bulk MongoDB $in queries and iterative BFS subtask traversal — 95–99% reduction in DB round-trips with zero API or schema changes.
- Replaced in-process concurrency limits with message-queue back-pressure for the AI agent service, decoupling HTTP handlers from run executors and eliminating silent job loss on pod restarts.
- Migrated core auth layer from synchronous ODM to async Motor/Beanie across 13 files, resolving event-loop blocking and unawaited-async ordering bugs in audit logs.
- Engineered LangGraph agentic workflows with LiteLLM processing 1B+ tokens/month of SEBI, RBI, and IRDAI regulatory data; built production RAG over financial regulations with versioned embeddings and citation grounding for clause-level retrieval over DRHPs and compliance circulars.
- Contributed to securing $4.2M Pre-Series A from PeakXV Partners through technical demos and executive presentations of ComplianceOS.
onfinance.ai ↗