Available · open to roles@ Publicis SapientShipping Bodhi Atomize

Shivang Singh.

>atPublicis Sapient

I build and scale GenAI systems in production — where latency, token limits, and failure modes matter as much as model quality.

Bengaluru, India
Production GenAI·LLM Infra·Computer Vision·FastAPI · K8s
Bengaluru · 12.97°N 77.59°E
Scroll
Production impact
10K+
assets processed
multimodal pipeline
95%
manual time cut
for Eli Lilly team
1K+
concurrent reqs
KEDA-autoscaled
$0.04
per Dossier run
8-agent pipeline
Snapshot

Currently building

Bodhi Atomize

Production multimodal GenAI platform decomposing 10,000+ marketing assets into 50+ structured signals per asset for Eli Lilly. Multi-stage LLM pipelines with token budgeting, backpressure, and KEDA-autoscaled microservices.

Gemini 2.5 ProClaude 4.6FastAPIKubernetesPyTorchPydantic
shipping· prod traffic since Jun 2025
Based in
Bengaluru, IN
IST · UTC+5:30
Last 7d focus
Recent ship
Dossier

8-agent job-search SaaS · 79 companies · ~$0.04/run · M4 wip

FastAPI· Clerk· Next 16
Daily driver
Python
PyTorch · FastAPI · Pydantic
pytsgosql
Currently

Obsessed with structured outputs, LLM evaluation, and production reliability under burst traffic.

Shipping daily
Coding to
Lo-fi · electronica · The xx
01 · About

I design and operate LLM pipelines that handle real traffic. At Publicis Sapient I lead Bodhi Atomize — a multimodal GenAI platform that turns images, videos, and GIFs into structured signals for enterprise clients like Eli Lilly. Previously shipped object detection and defect detection systems improving accuracy and inference speed at scale.

My work sits at the intersection of GenAI systems, computer vision, and production ML engineering — where latency, token limits, retries, backpressure, and failure modes matter as much as model quality.

Building AI that reliably works in production
Understanding failure modes early
Writing clean, scalable ML + backend code
Learning from real usage, not just papers
/ 01
95%
Manual analysis time cut
/ 02
10K+
Assets processed for Eli Lilly
/ 03
1K+
Concurrent requests handled
/ 04
1.21%
EER on biometric thesis
02 · Experience

Publicis Sapient
Current
AI Engineer · Senior Associate Data Science L1
Jun 2025 — PresentBengaluru, India
  • Architected Bodhi Atomize — production multimodal GenAI platform cutting marketing asset analysis from hours to ~2 min per asset (95% reduction) across 10,000+ assets for Eli Lilly. Outputs 50+ structured JSON signals per asset.
  • Engineered multi-stage LLM inference pipelines with Gemini 2.5 Pro and Pydantic-validated structured outputs. Implemented token budgeting, exponential-backoff retry, and backpressure control to sustain production throughput under rate limits.
  • Integrated YOLO and PaddleOCR into LLM workflows, extracting 50+ typed visual components (text, characters, emotions, branding) per asset. Established LLM evaluation with DeepEval (LLM-as-judge, G-Eval).
  • Built FastAPI microservices with Redis (caching + task queuing) and Celery. Deployed on Kubernetes with KEDA autoscaling to sustain 1,000+ concurrent requests under burst traffic with low latency.
Gemini 2.5 ProFastAPIPydanticYOLOPaddleOCRRedisCeleryKubernetesKEDADeepEval
Lincode Vision Labs
Data Science Intern → Trainee
Oct 2024 — Jun 2025Bengaluru, India
  • Integrated RF-DETR into production pipelines — 1.8× faster inference and +7% mAP50 improvement over YOLOv8 baseline on industrial defect detection.
  • Curated and preprocessed 30,000+ industrial images through targeted augmentation and annotation QA pipelines, lifting defect detection accuracy by 10%.
RF-DETRYOLOv8PyTorchOpenCV
Omdena
Junior Machine Learning Engineer
May 2024 — Aug 2024Remote
  • Led the supervised modelling team predicting urban farming zones in Milan using geospatial data.
  • Engineered XGBoost model achieving 93.68% accuracy. Conducted EDA on 106,000 rows with Geopandas.
  • Implemented real-time predictions, optimising data handling and model efficiency.
XGBoostGeopandasPython
Epoch · IIIT SriCity
Domain Lead — Computer Vision
Jan 2024 — May 2024Sri City
  • Led the Computer Vision domain for the campus AI/ML club. Mentored juniors, ran workshops, organized hackathons.
Matrix · IIIT SriCity
Co-Lead
Oct 2023 — May 2024Sri City
  • Co-led campus tech club. Organized events, hosted talks, fostered project-driven learning.
03 · Selected projects

/ project 01

Dossier

Quality-first agentic job-search SaaS

~$0.04
per pipeline run

8-agent autonomous pipeline (Persona Builder, Job Discovery, Watchlist, Company Intel, Gap Analysis, Market Intel, Resume Agent, Referral Finder) that finds, scores, researches, and surfaces roles most worth your time. Profile-driven scoring across 79 hand-picked companies, pre-LLM rule filter drops ~60% of jobs at zero cost, Claude generates ATS-optimised LaTeX resumes via 3-pass self-evaluation (Sonnet tailor → Haiku critic → Sonnet revise). M2+ wraps the CLI in a Next.js 16 + FastAPI + Clerk multi-user SaaS with credits, SSE progress, and async worker.

Python 3.12GPT-5.4-miniClaude Sonnet 4.6Claude Haiku 4.5FastAPINext.js 16ClerkTavilySSESQLiteLaTeX
View source
Case study
/ project 02

FedFV-CV

Federated Deep Learning for Biometric Auth

1.21%
EER

Federated deep learning framework for finger-vein biometric authentication using MobileNetV2. Engineered custom FedWPR aggregation on 122,600 images across 5 clients, outperforming FedAvg benchmarks. B.Tech Thesis, IIIT SriCity.

PyTorchMobileNetV2Federated Learning
View source
Case study
/ project 03

slackAgent

AI-Powered Slack Bot with RAG

40%
response time cut

Scalable FastAPI backend with LlamaIndex + ChromaDB semantic search over 20+ documents. Cut query response time by 40% and served 50+ daily queries via Slack API with end-to-end automation through n8n.

FastAPILlamaIndexChromaDBOpenAIn8n
View source
Case study
/ project 04

RAG-QA on AWS

Retrieval-Augmented QA, fully CI/CD

70B
params served

Retrieval-augmented QA system using LangChain, FAISS, and AWS Bedrock (LLAMA 3.1-70B). Deployed to AWS ECR + App Runner via Docker with full CI/CD through GitHub Actions.

LangChainFAISSAWS BedrockLLAMA 3.1-70BDockerGitHub Actions
View source
Case study
04 · Toolkit

LLM & GenAI

10 items
Gemini 2.5 ProGPT-5 / GPT-4oClaude Sonnet 4.6LangChainLangGraphLlamaIndexRAGPydanticPrompt EngineeringDeepEval

Computer Vision

5 items
YOLORF-DETRPaddleOCROpenCVMobileNetV2

MLOps & Backend

7 items
FastAPIDockerKubernetesKEDARedisCeleryMLflow

Cloud & Infra

8 items
GCPAWS BedrockAWS ECRApp RunnerAzureGitHub ActionsChromaDBFAISS

Programming & ML

6 items
PythonPyTorchscikit-learnpandasNumPySQL
Certifications
Google Cloud Computing Foundations: Data, ML, AI
Google Cloud Computing Foundations: Cloud Fundamentals
Google Cloud Computing Foundations: Infrastructure
Kaggle Pandas Certification
Stanford Unsupervised Machine Learning
AI Concierge
Live · grounded on resume

Skip the scrolling. Ask my AI anything about my production GenAI work, side projects, hiring fit, or technical decisions. Streams answers grounded only on my real experience.

Free · instant · no signup
Try one of these
Powered by Claude Sonnet 4.6 · streaming via Vercel
06 · Get in touch

Open to conversations around GenAI systems, LLM infrastructure, ML engineering, and production AI challenges. Drop a line — I reply fast.

© 2026 Shivang Singh · Bengaluru, IN
Next.jsTailwindMotionR3FAI SDK
v2.0 · last shipped Jun 2026