FOUNDING AI ENGINEER
LawWorld · Aug 2024 – Jun 2026
- Architected an Al Native Legal Tech Product end-to-end - production Al applications and scalable backend systems.
- Designed Agentic Al workflows and RAG pipelines serving 2,000+ users over a 170K-document corpus, prioritizing reliability, latency, and operational efficiency.
- Replaced a $12K/year vendor subscription in-house solo-building the agentic rich-text editor backend and its drafting orchestration layer - TipTap's paid Al toolkit only covered the editor surface, not the differentiating logic.
- Saved ~$500/month in cloud overhead building durable execution directly on MongoDB checkpoints and Azure Service Bus instead of adopting Temporal sustains 3-hour long-running agents with automatic crash-resume and zero data loss.
- Standardized on Model Context Protocol (MCP) for secure tool access deployed Dockerized servers in client VPCs with SSE tunnels for JSON-RPC schema discovery, executing agents without hardcoded tools or raw database credentials.
- Gated architecture decisions on strict blind-evals – defined accuracy/cost thresholds upfront against 550 production documents, forcing a data-driven choice between ReAct and structured-output rather than rationalizing decisions post-hoc.
- Held P99 latency at 50ms via an L2 Redis Stack semantic cache.
- Achieved a 20-30% hit rate on repetitive queries, offsetting ~$15,000/month in LLM inference spend using a $250/month cache at million-call scale.
- Fan-out parallel search cut retrieval latency 1.3s to 443ms then closed the multi-tenant gap structurally - session junctions are injected server-side into the vector pre-filter, so a query can narrow the search space but never widen it across tenants.
- Cut per-unit inference cost 5-10x via Swarm model-tiering - swapped GPT-5.2 for GPT-5.4-mini in extraction while keeping Qwen 3.5 for routing.
- Validated against versioned pricing across hundreds of legal Acts, scaling toward India's full statutory corpus.
- Blocked hallucinated-package execution across federated agents - implemented deterministic glass-box gates on an Agent-to-Agent (A2A) bus, running dependency-provenance checks against an allow-list before any untrusted payload executes.



