Senior AI/ML Engineer @ UST · Open to Senior AI/ML / Gen-AI / Research Roles

Shishir
Naaresh

LangGraph · AWS Bedrock · RAG Architectures · Causal ML · Graph Neural Networks

10+ years building production-grade ML systems, Generative AI pipelines, and large-scale analytics platforms across telecom, life sciences, and cybersecurity. Hands-on expertise in RAG architectures, LLM orchestration, AWS Bedrock, Causal Inference, and GNNs. M.Tech in AI/ML from BITS Pilani (A Grade, 2024). Now targeting Senior AI/ML Engineer, Gen-AI Engineer, and Research Scientist roles.

Years Exp.
DS / ML Yrs
Excellence Awards

Knowledge graph · drag to rotate

Scroll

Who I am

About Me

I'm a Senior AI/ML Engineer with 10+ years of experience building production-grade ML systems, Generative AI pipelines, and large-scale analytics platforms. Currently at UST, delivering LLM-powered multi-tenant chatbot platforms, document-aware RAG systems, and Vision AI pipelines for clients like Nokia and AT&T.

My work spans Telecom (2+ yrs) — ReAct/MRKL agentic architectures, Causal Double ML, Graph Neural Networks, and Vision AI for network optimisation — Cybersecurity (2+ yrs) — anomaly detection, ETL pipelines, and AWS-orchestrated analytics at Accenture — and LifeSciences (6 yrs) — genomics Knowledge Graphs, RAG pipelines over genomic literature, biomarker ML models, and clinical trial data engineering at TCS.

I hold an M.Tech in AI/ML from BITS Pilani (A Grade, 2024), with proven impact: reduced Vision AI pipeline runtime by 83%, cut tool integration from 1 week to 1–2 days, and reduced false tool calls by 40% through architectural improvements in production systems.

Targeting roles like
🧠
Senior AI/ML EngineerLangGraph · AWS Bedrock · RAG · LLM Orchestration · Agentic AI
🔬
Research Scientist — LifeSciences AIKnowledge Graphs · Genomics · Causal Inference · GNN · NLP
☁️
Gen-AI / MLOps EngineerRAG Architectures · AWS Bedrock · GCP Vertex AI · BigQuery · MLOps
Gen-AI · RAG · LLM Orchestration · RAG Data Modelling85%
Statistical ML · Classical Models · Deep Learning · NLP(Natural Langugage Processing)98%
Model Serving (Flask / FastAPI)82%
Knowledge Graphs (Neo4j) · Qdrant (Vector Database)87%
ETL · Data Pipelines · Cloud90%
Python · Pandas · EDA · Backend Development91%
Experience by domain
9+
yrs

Technical Arsenal

Skills & Tools

🧠
Gen-AI & LLM Engineering
LangGraphLangChainAWS BedrockRAG PipelinesPrompt EngineeringAgentic AITool OrchestrationReAct/MRKLMulti-Hop Reasoning
📊
ML / DL / Statistics
PyTorchTensorFlowScikit-learnCausal Double MLGraph Neural NetworksBERT/TransformersAnomaly DetectionNLP/NERHypothesis Testing
🚀
Model Serving & APIs
FastAPIFlaskREST APIJWTDockerAWS LambdaGCP Cloud RunPySpark
🕸️
Knowledge Graphs & Vector DBs
Neo4jCypherKnowledge GraphsQdrantVector EmbeddingsGraph RAGSemantic Modelling
☁️
Cloud & Data Engineering
AWS BedrockGCP Vertex AIBigQueryDatabricksKafkaStep FunctionsFargateCloudWatchPostgreSQLMongoDB
🔬
Tooling & DevOps
PythonGITAzure DevOpsTableauDockerAmazon TitanAmazon Nova LiteFeature Engineering

Academic Background

Education

M.Tech — Artificial Intelligence & Machine Learning
BITS Pilani (Distance Learning)
A Grade
2022 – 2024
B.Tech — Electrical Engineering
Uttarakhand Technical University, Dehradun
75.6%
May 2015
Class XII
St. Mary's Sr. Sec. School · CBSE, Haridwar
85.6%
2011
Class X
St. Mary's Sr. Sec. School · CBSE, Haridwar
90%
2009

Career Journey

Work Experience

AI/ML Engineer
UST · Noida  ·  Client: Nokia
Nov 2024 – Present
PythonFastAPIFlask LangGraphAWS BedrockRAG GCP Vertex AIPyTorchTensorFlowNeo4jQdrant
GenAI LLM-Based Multi-Tenant Chatbot Platform · Network Optimization & Automation
  • Re-architected the core agent from monolithic LangGraph to a ReAct + MRKL-based architecture, enabling parallel and sequential multi-tool execution — decoupling tool orchestration from business logic and improving throughput on complex multi-step queries.
  • Cut tool integration time from 1 week to 1–2 days by building a JSON-configuration-driven tool registry — developers define only a config schema and request formatter; all routing, orchestration, and validation handled automatically by the framework.
  • Built a global shared cache layer (30-min TTL, cross-session) with pre-dispatch parameter validation — reduced false tool calls by ~40% and lowered downstream server load for better scalability.
  • Replaced all hardcoded intent-matching logic with 10-turn rolling conversation context, enabling robust handling of ambiguous multi-turn queries without rule-based fallbacks.
In-House RAG Ingestion, Querying & Lifecycle Management Platform
  • Architected a production-grade, document-type-aware RAG platform with tailored ingestion strategies per format — Excel/tabular (column, sheet, row granularity converted to header-enriched natural language), PDF/Word (overlapping sliding-window + semantic chunking), and XML (parent-child relationships as chunk metadata).
  • Built a multi-technique querying pipeline — Multi-Hop Reasoning, Query Compression, Entity-Based Search, Query Rewriting, and Re-ranking — resolving relational queries via an in-memory knowledge graph built at query time.
  • Designed a metadata-driven document lifecycle system with version and document-identity metadata on chunks, enabling targeted deletion/replacement on update and eliminating full re-ingestion.
Vision AI — Pole Height & Feature Extraction Pipeline · AT&T AIO Project
  • Designed a scalable async Vision AI pipeline on GCP to extract telecom pole attributes from 2D/3D street imagery using geo-coordinates, processing thousands of images per batch.
  • Reduced pipeline execution time for 4–5K images from ~4 hours to ~40 minutes (~83% reduction) by introducing a Vertex AI Session Pool — distributing inference across concurrent API sessions instead of serialised single-session calls.
  • Implemented a Circuit Breaker pattern at the session level — rate-limit failures pause the affected session while traffic reroutes to healthy sessions, preventing cascading failures and full pipeline restarts.
AWS Bedrock LLM Chatbot — Intelligent Site Alarm & Status Assistant
  • Designed an end-to-end LLM chatbot on AWS Bedrock for Nokia site engineers — enabling natural-language querying over alarm resolution guides and site status parameters, significantly reducing dependency on customer support.
  • Built a secure, encrypted Bedrock Knowledge Base backed by S3 with Amazon Titan embeddings and Amazon Nova Lite for inference, applying semantic chunking for high-fidelity document ingestion.
  • Designed a Bedrock Agent with intelligent routing logic to dynamically decide — based on user intent — whether to query the knowledge base or invoke AWS Lambda functions to fetch live site parameters and alarm status in real time.
Network Optimization — Causal ML, Fault Forecasting & Graph Neural Networks
  • Implemented Causal Double Machine Learning (DML) to isolate parameters with true causal impact on spectral efficiency, eliminating spurious correlations from high-dimensional KPI features.
  • Addressed class imbalance and noisy labels in telecom fault alarm forecasting, improving F1-score through targeted resampling and label-cleaning strategies.
  • Modelled telecom network data as knowledge graphs and trained Graph Neural Network models for anomaly detection and event prediction.
Senior Software Engineer
Accenture · Noida
Mar 2022 – Nov 2024
PythonTypeScript PySparkGoogle BigQueryKafka AWSStep FunctionsCloudWatchPostgreSQL
Information Security Analytics Dashboard · Cybersecurity Domain
  • Architected ETL ingestion pipelines centralising multi-source security telemetry; executed end-to-end migration from MySQL → PostgreSQL → Google BigQuery, improving query performance and analytical scalability.
  • Led architecture redesign for real-time sync between PostgreSQL backend and BigQuery frontend using Kafka, maintaining both in sync without downtime.
  • Designed statistical anomaly-detection models (isolation forest, z-score baselines, time-series decomposition) and orchestrated pipelines via AWS Step Functions with CloudWatch alerting for model drift and data-quality failures.
  • Built EDA and reporting layers translating model outputs into executive-level insight dashboards for security leadership.
IT Analyst
Tata Consultancy Services · Noida
Jan 2016 – Mar 2022
PythonFlaskNode.js Neo4jKnowledge GraphsRAG AzureMongoDBSpring Boot
Genomics Knowledge Graph Platform · LifeSciences Domain · May 2019 – Mar 2022
  • Architected a RAG pipeline over genomic literature using Neo4j as graph store, vector embeddings for semantic retrieval, and an ML synthesis layer — enabling natural-language Q&A over biological datasets; co-authored white paper on semantic knowledge graph modelling for clinical genomics.
  • Designed Knowledge Graph schemas for genomic entities (genes, proteins, pathways, phenotypes); trained ML models (random forest, gradient boosting) for biomarker classification; deployed via Flask REST APIs with JWT security.
Azure ITSM Chatbot & Telecom Call Failure RCA · Jan 2018 – Apr 2019
  • Built an Azure ITSM chatbot with multi-step dialog, ServiceNow integration, Image-to-Text AI inference, and Cortana voice channel — deployed across MS Teams, Skype, and Direct Line.
  • Built an end-to-end RCA pipeline classifying call failures and voicemail drops from TAS, AMF, and MME logs across millions of call events — reconstructing complete call lifecycles using unique call identifiers and engineering features capturing timing, signalling, and failure-mode patterns.
Clinical Trial Digitalization · LifeSciences Domain · Apr 2016 – Jan 2018
  • Built data sync pipelines for clinical trial digitalization aggregating data from multiple heterogeneous sources with statistical quality checks (distribution tests, outlier detection).
  • Implemented GridFS MongoDB streaming API for chunked upload and playback of clinical multimedia data. Led ILP project team — awarded ILP LIREL Best Associate During Training.

Research & Engineering Work

Projects

PROJECT 01 · RESEARCH

Genomics Knowledge Graph Platform

End-to-end KG system for LifeSciences genomics research — ingestion, semantic modelling, and interactive visualisation.

Neo4jKnowledge GraphSpring BootPython
Explore project
PROJECT 02 · AI ENGINEERING

AI-Powered ITSM Chatbot

Enterprise chatbot with Image-to-Text AI inference, ServiceNow integration, voice channel, and multi-cloud deployment.

Node.jsBot FrameworkAzureImage-to-Text AI
Explore project
PROJECT 03 · DATA ENGINEERING

Information Security ETL Dashboard

Cloud-native ETL platform ingesting multi-source security telemetry with AWS Step Functions orchestration and live analytics.

PythonMySQLAWSETL
Explore project
PROJECT 04 · LIFESCIENCES

Clinical Trial Digitalization

Multi-source data synchronisation system and GridFS MongoDB streaming API for digitising clinical trial workflows.

JavaMongoDBREST APINode.js
Explore project
PROJECT 05 · GEN-AI · AGENTIC AI

LLM-Based Multi-Tenant Chatbot Platform

ReAct + MRKL agentic architecture with JSON-config-driven tool registry, cross-session cache, and rolling context — reducing tool integration from 1 week to 1–2 days and false tool calls by 40%.

LangGraphLLMRAG PythonReAct/MRKL AWS Bedrock
Explore project
PROJECT 06 · RAG · DOCUMENT INTELLIGENCE

RAG Ingestion & Lifecycle Management Platform

Production-grade, document-type-aware RAG platform with tailored ingestion strategies per format (Excel, PDF, XML), multi-technique querying pipeline, and metadata-driven document lifecycle management — eliminating full re-ingestion on updates.

PythonQdrantRAG LLM
Explore project
PROJECT 07 · VISION AI · GCP

Vision AI — Pole Feature Extraction Pipeline

Scalable async GCP pipeline extracting telecom pole attributes from 2D/3D street imagery. Achieved 83% runtime reduction (4 hrs → 40 min) via Vertex AI Session Pool and Circuit Breaker pattern for fault-tolerant inference at scale.

PythonGCPVertex AI Computer VisionCloud RunCloud Tasks
Explore project
PROJECT 08 · AWS BEDROCK · GEN-AI

AWS Bedrock LLM Chatbot — Site Alarm & Status Assistant

End-to-end LLM chatbot on AWS Bedrock for Nokia site engineers — intelligent agent routing between a secure Knowledge Base and live Lambda-fetched site data, eliminating repetitive customer support escalations.

AWS BedrockLambdaAmazon TitanPythonS3CloudWatch
Explore project

Recognition

Awards & Honours

🏆
Innovation Pride AwardTCS · Feb 2021
🥇
Service & Commitment AwardTCS · Jan 2021
Technical Excellence AwardTCS · Aug 2020
🤝
On the Spot (Team) AwardTCS · Aug 2020
👏
Applause for Team AwardTCS · Aug 2020
🎯
On The Spot AwardTCS · June 2017
🌟
ILP LIREL — Best Associate During TrainingTata Consultancy Services · July 2016

Get in touch

Let's Connect

⚙ Portfolio Admin

💡 Edit skills as comma-separated values. Changes apply live on save.
💡 Click a project to edit its full modal details. All changes persist for this session.
01 · Genomics Knowledge Graph Platform
02 · AI-Powered ITSM Chatbot
03 · Information Security ETL Dashboard
04 · Clinical Trial Digitalization
05 · LLM-Based Multi-Tenant Chatbot Platform
06 · RAG Ingestion & Lifecycle Management Platform
07 · Vision AI — Pole Feature Extraction Pipeline
08 · AWS Bedrock LLM Chatbot — Site Alarm & Status Assistant
✓ Saved successfully