Post Job Free
Sign in

AI/ML Engineer RAG Search Knowledge Graph Agentic AI

Location:
Sunnyvale, CA
Salary:
80000
Posted:
August 14, 2025

Contact this candidate

Resume:

SURAJ PHANINDRA

AI/ML Engineer

+1-408-***-**** **********@******.*** https://www.linkedin.com/in/suraj-phanindra-979907205/ https://github.com/suraj-phanindra Sunnyvale, CA US Citizen SUMMARY

Innovative AI/ML Engineer with founding team experience building production-grade generative AI systems from the ground up. Demonstrated expertise in RAG architectures, vector databases, and knowledge graph implementations that directly impact business metrics. Strong track record of leading technical teams and architecting scalable MLOps infrastructure on AWS. Combines entrepreneurial mindset with deep technical expertise. EDUCATION

B.E(Honours) in Computer Science

BITS Pilani, Pilani Campus

11/2020 - 07/2024 Pilani, RJ, India

Licensee & Head Organizer, TEDxBITSPilani.

Postman API Programming Classroom Program Student Expert. EXPERIENCE

AI/ML Engineer - Internship converted into Full-time position Webless

07/2024 - Present Gurgaon, India

https://www.webless.ai/

Webless offers an AI-powered search bar & content discovery engine that brings the power of semantic search to any website aiming to turn visitors into buyers by surfacing relevant content.

ETL Pipeline Architecture: Built automated content ingestion system using AWS Step Functions and Lambda with multithreaded data enrichment, achieving

; presented system at Web Summit

Lisbon 2024, demonstrating end-to-end sitemap-to-searchbar 8x performance

improvement (4 hours to 30 minutes for 100 URLs)

deployment in <5 minutes.

Knowledge Graph Architecture: Led design and implementation of metadata knowledge graph using Neo4j, including data modelling, node extraction pipeline, relationship mapping, and CYPHER query optimization for technical asset retrieval. Product Lead - Landing Page Personalizer: Spearheaded development of real-time page personalization engine leveraging user profiling and cached content variants, achieving persona-based content delivery at scale.

Analytics & Monitoring Stack: Designed comprehensive logging infrastructure using AWS CloudWatch, Athena, and Glue; implemented sub-second API performance monitoring and user behavior heatmap visualization tools.

Vector Database Optimization: Executed migration of from multiple Pinecone indexes to single multi-tenant namespace architecture; developed retrieval quality evaluation framework measuring semantic similarity, chunk quality, URL coverage, and factual accuracy and generation quality evaluation framework measuring accuracy, consistency and hallucination detection.

200,000+ vectors

Full-Stack Infrastructure: Configured production AWS environment (auto-scaling groups, CloudFront CDN, load balancers, EC2 launch templates, Bedrock for MLOps). Session Intelligence: Developed session-aware follow-up question generation, dynamic CTA recommendation algorithms, and conversation history context weighting for enhanced retrieval performance.

Lead Developer (Full Stack) - University Internship Alankaar

05/2022 - 08/2022 Delhi, India

https://suraj-phanindra.github.io/Alankar-Web/

Alankaar is a not for profit company that aims to provide effective modern education and essential skills to underprivileged children in India. Technical Leadership: Led 12 interns in delivering full-stack MERN application for company digitization; served as liaison between executive and development teams ensuring project completion.

Increased overall timely task completion rate by 20%. Co-Founder and CTO - Self Employed at Startup

AirStamp

09/2020 - 08/2023 Bangalore, India

https://tinyurl.com/39jmmbz8

AirStamp is an all-in-one access credential application that aims to provide seamless check- in, foot traffic data, and customer identity validation services using BLE beacons and a mobile application.

Wadhwani Foundation IGNITE Entrepreneur Challenge 2021 Winner. Secured Incubation resources and initial venture funding from Wadhwani Foundation. Received provisional patent in India for BLE beacon application. Hired and managed a team of five people working remotely spread across the globe, ensuring enforcement of NDA and protection of IP.

SKILLS

Languages

Python Java C++/C# CYPHER

SQL AWS States Language JavaScript

PineScript

Technologies

NLP LLM Vector DB REST API

Embeddings Langchain CI/CD

MongoDB Graph DB Fine-tuning

Clustering Redis FastAPI RAG

Infra & Operations

AWS Docker Scrum Agile GIT

Kubernetes Blockchain/DAO

PROJECTS

Automated Dietary Recommendations

Based on Medical Prescriptions

03/2024 - 05/2024 BITS Pilani, India

https://tinyurl.com/yvtdymwf

Extracted text from medical prescriptions using

Tesseract OCR and PyPdfium.

Predicted diseases with AdaBoost classification

models and Gemini.

Provided dietary recommendations using

clustering models and LLM, based on online

sources.

Song recommendation Web App using

Spotify APIs

11/2021 - 12/2021

Postman API Lab, BITS Pilani, India

https://lnkd.in/g3-YWDgb

Generates personalized song recommendations

based on three seed artists.

Created a web application using Glitch as the

hosting platform and Axios, Bootstrap,

Node.js/Express.js for development and

OAuth2.0 for token generation and validation.

Blockchain-based Supply Chain Traceability

for Pharmaceutical Products

09/2023 - 11/2023 BITS Pilani, India

https://github.com/suraj-phanindra/Blockchain-

Project

Designed a blockchain-based system to trace

the complete supply chain for pharmacy firms,

capturing manufacturing details, quality checks,

distribution, and side effect history.

Ensured data integrity and security throughout

the process, enabling reliable tracking from

manufacturing to delivery.



Contact this candidate