Shipping Production AI Systems

Purvesh Patidar

I build low-latency, production-grade LLM systems with real-time streaming and deterministic orchestration.

85 tokens/sec streaming • <50ms TTFT • 95% test coverage

Architecting for
Scale & Reliability.

State & Infra

MongoDB, Redis, Docker, WebSocket tuning handling 1k+ daily peak CCUs.

Architecture

Node.js/FastAPI hybrid services for optimized ML inference & reliable data delivery.

Product-focused
Generative AI.

  • Predictive Forecasting94% Accuracy
  • Course Recommendation+22% Engagement
  • Sentiment ClassifierStreamlit UI

Production Experience

Engineering Case Studies

Production systems with measurable performance, real constraints, and engineering tradeoffs.

01

AI Agent — LangGraph Agentic RAG System

Low-latency streaming RAG with deterministic orchestration and measurable reliability.

85 tokens/sec Streaming Throughput
LangChainLangGraphPython 3.10+
02

RAG-Powered Document Q&A Chatbot

Fast, source-attributed document QA across multi-PDF corpora with sub-second retrieval.

< 40ms Vector Search Latency
LangChainChromaDBPython
03

LLM Chatbot Integration Dashboard

Production LLM assistant that reduced support friction via structured, context-aware responses.

< 20ms Session Cache Latency
OpenAI APIHugging FaceNode.js

Impact

Performance you can feel

Streaming throughput85 tokens/sec

Measured on GPT-4-class models with ~20 concurrent SSE clients (representative load).

Time to first token<50ms

Measured from request accepted to first SSE token (warm path).

Test coverage95%

Integration + evaluation harness coverage across agent flows and regressions.

End-to-end latency<1.5s

Retrieval + generation + response assembly for document Q&A scenarios.

Vector search latency<40ms

Retrieval step latency for typical query vectors (embedding precomputed).

Engineering Decisions

The choices behind the outcomes

Why LangGraph over traditional agents

I prefer explicit graphs over opaque agent loops. Nodes and state transitions make orchestration deterministic, debuggable, and testable under real failure modes.

Tradeoff: It requires up-front workflow modeling and ongoing state-schema maintenance as capabilities evolve.

Why SSE for streaming

For real-time token streaming, SSE keeps the path simple and HTTP-native. It works cleanly with typical proxies/LBs and keeps the client implementation lightweight for server->client updates.

Tradeoff: SSE is not full duplex; if you need true bidirectional messaging, WebSockets can be a better fit.

Why ChromaDB vs alternatives

For many RAG workloads, I optimize for iteration speed and predictable retrieval behavior. ChromaDB is a pragmatic vector store for development and smaller deployments without heavy operational overhead.

Tradeoff: At higher scale or strict HA needs, you may need to migrate to a managed/distributed vector database.

Why deterministic outputs (and validation) matter

I avoid systems that cannot be reliably parsed, tested, or monitored. Structured outputs plus validation make failures explicit and keep UX stable as models drift.

Tradeoff: Stricter constraints add prompt complexity and may require retries when the model deviates from the schema.

How I Think

Opinionated engineering, shipped.

I build production LLM systems that are fast, inspectable, and predictable under load. If it cannot be measured or tested, it does not ship.

  • What I optimize for

    • Low latency and fast time-to-first-token
    • Deterministic orchestration over "magic"
    • Observability: traces, metrics, and replayable evals
  • What I avoid

    • Black-box agents with unclear control flow
    • Untestable prompts and "it works on my machine" demos
    • Latency surprises hidden behind async complexity
  • How I approach tradeoffs

    • Pick the simplest architecture that meets the SLO
    • Make the failure modes explicit (timeouts, fallbacks, budgets)
    • Measure first, then optimize with guardrails

Active R&D

Currently Building

Exploring agent orchestration patterns that balance flexibility with deterministic control.

  • Multi-step agent workflows with observable state transitions
  • Cost-aware RAG pipelines with dynamic retrieval strategies
  • Evaluation systems for measuring LLM output quality at scale

Focus is on making these systems production-ready — not just experimental.

RAG_PIPELINE.EXEC()

Work With Me

Ready for the next build.

I’m focused on building production-grade AI systems, backend architecture, and real-time LLM applications.

If you’re working on something challenging in this space, let’s talk.

Prefer email? I reply fast to concise, technical messages.