Open to opportunities
  • New York

Hi there, nice to meet you.

Rishi Chhabra

I'm an AI engineer based in the New York metro area. I focus on the infrastructure and platforms that help teams build and run AI systems.

Download resume ↓ Email me ↗

01 About me

Portrait of Rishi Chhabra
New York metro area

At Ikka Labs, I build AI-native platforms and internal developer tools. I've worked on a self-service platform that helps engineering teams provision data and inference services, and an AI code-review agent that fits into their existing workflows.

I completed my M.S. in Machine Learning at Stevens Institute of Technology in May 2026. Before graduating, I worked as an AI Engineer at AriesView, where I built a chatbot for a collection of real estate documents and worked on caching with Valkey.

Based in
New York metro area
Focus
AI infrastructure and platform engineering
Current role
AI Engineer at Ikka Labs
02 Work

Where I've shipped.

New York metro area
  • Built a self-service onboarding platform that lets teams provision data and inference services across on-premises Kubernetes, Amazon EKS, and Azure AKS.
  • Built an AI code-review agent that teams can add to their repository workflows on GitHub, GitHub Enterprise Server, and other repository providers. It connects to their chosen LLM provider using credentials managed in HashiCorp Vault, and can run according to each team's configured triggers.
Ikka Labs · 2026
Boston, MA
  • Built a chatbot that uses information retrieved from the company's real estate documents to answer questions.
  • Improved document retrieval by combining keyword and semantic search.
  • Worked on Valkey caching to improve API response times.
AriesView · 2025
03 Projects

Built on my own time, measured anyway.

01

Cost-Aware Semantic Gateway for LLM Routing

A lightweight classifier estimates how complex each request is, then routes it to a local or hosted model. Simpler requests stay local; more complex ones go to GPT-4o.

68.1%lower cloud-model spend
79%of requests stayed local
93.4%routing accuracy

In an 81-query benchmark, 79% of requests stayed local and cloud-model spend was 68.1% lower than an all-GPT-4o baseline. Routing accuracy on labeled prompts was 93.4%, which measures query classification, not answer quality.

FastAPI · vLLM · Llama 3.2 · GPT-4o · Streamlit · Docker Source ↗
02

Automated LLM Evaluation and Observability Pipeline

I built this pipeline to catch quality regressions in RAG systems during code review. It scores faithfulness, answer relevancy, and contextual precision, and blocks a merge when any metric falls below its configured threshold.

95%threshold for each metric
3metrics per pull request

Each metric must score at least 95%. That's a merge gate, not a measure of overall answer accuracy.

RAGAS · DeepEval · LangSmith · GitHub Actions · Claude Haiku Source ↗

04 Technical Skills

Cloud and containers

  • Kubernetes
  • Docker
  • OpenShift
  • AWS
  • Amazon Bedrock
  • Azure

Infrastructure and delivery

  • Terraform
  • Kustomize
  • GitHub Actions
  • GitLab CI/CD
  • MLflow
  • Kubeflow
  • OAuth 2.0/OIDC
  • RBAC
  • HashiCorp Vault

AI inference and serving

  • vLLM
  • llm-d
  • Ollama
  • GPT-4o
  • Llama
  • Gemini
  • PyTorch
  • Hugging Face

Retrieval and evaluation

  • RAG
  • GraphRAG
  • Hybrid search
  • BM25
  • Semantic chunking
  • Cohere reranking
  • LangChain
  • LangGraph
  • MCP
  • Tool calling
  • ReAct
  • RAGAS
  • DeepEval
  • LangSmith
  • LLM-as-a-judge

Backend and data

  • Python
  • SQL
  • JavaScript
  • Linux
  • FastAPI
  • PostgreSQL
  • Valkey
  • Redis
  • ElastiCache
  • Kafka
  • Weaviate
  • Neo4j

05 Education

Degrees

Stevens Institute of Technology

M.S. in Machine Learning · Hoboken, New Jersey

September 2024 to May 2026
  • Artificial Intelligence
  • Natural Language Processing
  • Deep Learning
  • Computer Vision
  • Big Data

Central University of Haryana

B.Tech. in Computer Science · India

September 2020 to June 2024
  • Data Structures
  • Operating Systems
  • Database Systems
  • Computer Networks
  • Cloud Computing
  • Linux/Unix

Certifications

  • Databricks Certified Generative AI Engineer2026
  • Anthropic Claude Certified Architect, Foundations2026
  • AWS Certified Machine Learning Engineer, Associate2025
  • AWS Certified Developer, Associate2025
  • Databricks Certified Associate Developer for Apache Spark2025
06 Contact

Want to work together? Say hello.

I'm open to opportunities building AI systems and platforms, including AI engineering, MLOps, and forward deployed roles. I'm based in the New York metro area and open to relocating. Email is the best way to reach me.

Rishi.Chhabra@outlook.com
Download resume ↓ GitHub ↗LinkedIn ↗Medium ↗