Available for opportunities

Vivek Singh

I architect and build autonomous AI systems -- from multi-agent orchestration to production-grade RAG pipelines -- powered by LLMs, LangChain, and AWS infrastructure. Turning complex AI research into scalable, real-world solutions.

0+
Years in Production
FX & AI Engineering
0
AI Agents Built
Live LangGraph pipelines
0
Hollywood Productions
Transformers · Ant-Man · Crater
0
Certifications
DataCamp · AI & Python

The Through Line

From Procedural to Agentic

Every concept from 3 years of FX pipeline engineering maps directly to modern AI systems. The vocabulary changed. The thinking did not.

"A Houdini network and a LangGraph are the same data structure, a directed graph of composable nodes. I switched from simulating fire to orchestrating reasoning."
FX

Houdini SOP Network

Node-based DAG for geometry processing

AI

LangGraph StateGraph

Node-based DAG for agent orchestration

Insight: Both are directed graphs of composable, stateless processing nodes — same data structure, different domain.

FX

VEX Kernels

Data-parallel compute over point clouds

AI

LLM Tool Functions

Discrete compute units called by agents

Insight: Atomic, typed, side-effect-free functions. Write once, reuse anywhere in the graph.

FX

Procedural Simulation

Parameterized, reproducible, non-destructive

AI

RAG Pipeline

Parameterized, reproducible, modular retrieval

Insight: Change one upstream parameter and everything downstream updates deterministically.

FX

Unreal Blueprints

Visual state machine for runtime logic

AI

Agent Conditional Edges

Routing logic between graph nodes

Insight: Event-driven state transitions: if condition X, go to node Y. Identical pattern.

FX

Realtime VFX (<16ms)

Hard latency budget per frame

AI

Production LLM API (<500ms)

Hard latency SLAs for UX

Insight: Both demand performance-first thinking: cache aggressively, batch, optimize hot paths.

FX

Asset Pipeline Automation

Python ingesting raw assets to rendered outputs

AI

ML Data Pipeline

Python ingesting raw docs to vector embeddings

Insight: ETL with domain-specific transforms. Same architecture, different data types.

This is not a career pivot. I spent 3 years thinking in graphs, writing Python automation, and shipping under hard deadlines. The domain changed. The way I approach problems did not.Same mindset. Different tools. Already proven under pressure.

Expertise

Technical Stack

Deep expertise across the full AI stack -- from model training and prompt engineering to cloud infrastructure and production deployment.

Core AI / ML

Building intelligent systems from the ground up

LLM Fine-tuningPrompt EngineeringRAG PipelinesVector DatabasesMulti-Agent Orchestration

Frameworks

Production-grade tools and libraries

LangChain / LangGraphAWS BedrockFastAPINext.jsHugging Face

Languages

Writing clean, efficient code

PythonTypeScriptSQLBash

Cloud & Infra

Deploying at scale with reliability

AWS LambdaECS FargateSageMakerDocker / K8sTerraform

Data & Storage

Managing data pipelines and persistence

PineconeDynamoDBS3Redis / ElastiCachePostgreSQL

Orchestration

Connecting systems together

Step FunctionsEventBridgeSQS / SNSCloudWatchCI/CD

Selected Work

Featured Projects

Production AI systems built for scale, reliability, and real-world impact.

Featured

Multi-Agent Research System

Autonomous research pipeline using LangGraph with specialized agents for query decomposition, web search, and synthesis. Self-correcting loops with confidence-based routing.

LangGraphGPT-4FAISSAWS Lambda
50k+ daily queries
94% accuracy
< 200ms p99

RAG-Powered Knowledge Base

Production RAG system with hybrid search (BM25 + vector), query rewriting, and cross-encoder reranking deployed on AWS ECS.

LangChainPineconeAWS ECSFastAPI

Resume Screening Agent

Agentic workflow that parses resumes, extracts structured data, and scores candidates against job descriptions using chain-of-thought reasoning.

OpenAIPydanticS3DynamoDB

Let's Connect

Interested in working together?

I'm currently open to new opportunities in Agentic AI, GenAI Architecture, and LLM Systems Engineering. Let's build something impactful.

hello@viveksingh.tech