Kaushik Kumar.
Building Production Compound AI Systems.
I am an AI Engineer with an M.S. in Computer Science (Specialization in Artificial Intelligence) from NJIT. I architect production-grade Agentic AI systems, scalable MLOps, and deterministic multi-agent workflows that transform advanced research into measurable business ROI.
The Production Reality
Building a slick LangChain prototype takes a weekend. Deploying an autonomous multi-agent system that executives actually trust requires a totally different paradigm. My focus is entirely on the broken middle-tier: reliability, safety, and Total Cost of Ownership (TCO).
Deterministic Safety Rails
LLMs are probabilistic; enterprises need deterministic outcomes. I architect strict schema validation boundaries, PII filtering, and multi-layered jailbreak prevention to ensure agents never hallucinate catastrophic actions.
Deep Observability
If you can't trace it, you can't trust it. I build telemetry-first systems utilizing Arize Phoenix and Langfuse to monitor token usage, latency, and agent reasoning traces down to the individual span level.
Business ROI & TCO
I optimize models and vector queries not just for accuracy, but for cost. Transitioning from generic heavy APIs to specialized, self-hosted LLMs and intelligent routing drastically reduces inference costs while scaling.
Professional Experience
AI Engineer @ FIELDWORKER.AI
Feb 2026 - May 2026The Challenge: Automating complex SDR document extraction securely while eliminating the risk of unverified LLM actions.
The Architecture: Built an end-to-end agentic parsing system via a self-hosted LLM with check-then-update wrapper endpoints and a Human-in-the-Loop (HITL) validation UI.
The Business Impact: Slashed manual data entry time from hours to under 3 minutes per document, completely eliminated unauthorized API access risks, and enabled concurrent SDR workloads at scale.
Software Engineer Intern @ CISCO SYSTEMS, INC.
Feb 2024 - Jun 2024The Challenge: The CCW Renewals team faced bottlenecked financial operations and slow response times under peak traffic loads.
The Architecture: Designed scalable Spring Boot microservices incorporating optimized caching mechanisms and asynchronous processing logic.
The Business Impact: Increased operational efficiency by 20% across 500+ enterprise accounts, reduced database load by 45%, and cut production errors by 40% via strict TDD coverage.
ML Engineer @ VERZEO EDUTECH PVT. LTD.
Feb 2023 - Mar 2023The Challenge: Existing predictive models were slow and resource-intensive during real-time image and time-series inferences.
The Architecture: Engineered and tuned real-time CNN/RNN models deployed as containerized microservices on GCP with batch inference caching.
The Business Impact: Improved prediction accuracy by 15%, reduced latency by 25%, and scaled resources to support a 50% higher workload capacity during peak usage.
Featured Architecture
The Problem: Unreliable, hallucinating analytics agents eroding executive trust.
Technical Leap: Built a 6-node deterministic LangGraph architecture with self-correcting SQL generation.
Outcome: Achieved 100% routing accuracy and zero-data-exfiltration security.
Project Archive
Implemented an any-to-any multimodal LLM architecture, bridging the gap between text, image, and audio inputs for unified, complex reasoning.
Engineered scalable LangChain abstractions backed by a Postgres database, drastically improving memory persistence and retrieval speeds for production agents.
Built an advanced RAG implementation featuring automated RAGAS evaluation to ensure strictly quantified relevancy and faithfulness scores before deployment.
Skills & Arsenal
Agentic AI & Prompting
Machine Learning & RAG
DevOps, Cloud & DBs
AI Safety & Observability
Education
Master of Science in Computer Science
New Jersey Institute of Technology (NJIT)
Sep 2024 - May 2026Focusing on Advanced Machine Learning, AI Systems, and Scalable Architectures.
Bachelor of Engineering in Information Science and Engineering
BMS College of Engineering
Sep 2020 - Jun 2024Core focus on Algorithms, Data Structures, and Software Engineering.