MG.
Available for opportunities & freelance projects

I build AI systems that save teams real time and money. From intelligent assistants that handle 90%+ of support queries to agentic pipelines that cut manual work by 70%, I focus on what matters after the demo: latency, reliability, and measurable cost reduction.

Get in Touch View Work
Maanik Garg
Scroll
About Me

Making AI work
where it matters most

AI/ML Engineer based in Frankfurt am Main, with a Master's in Data Science and 5+ years building machine learning solutions across production environments. I've spent my career at the intersection of ML and product engineering, building systems that don't just demo well but hold up in production under real traffic.

At WAMOCON, I lead the AI engineering effort: building the company's on-premises AI platform on a private GPU cluster, designing intelligent assistants that resolve support tickets without human intervention, and shipping agentic workflows that replaced entire manual processes. I also deliver client systems on the same foundation, from an on-premises assistant for a tax-advisory firm that keeps confidential data fully in-house to an AI-driven operations platform for a real-estate firm. I care about clean architecture, fast iteration, and results you can measure in saved hours and reduced costs.

Outside my full-time role, I'm Co-Founder and CTO of PawVerse, an AI veterinary healthcare platform live in production. I also take on freelance AI engineering, from email and workflow automation that removes manual work to full-stack development. Open to freelance projects in AI, automation, and software engineering.

neural network
data pipeline
inference
5+
Years in Production
70%
Faster Workflows
90%
Tickets Resolved by AI
3x
Output per Sprint
Career Path

Where I've delivered impact

AI Engineer
Aug 2024 - Present
WAMOCON GmbH, Frankfurt, Germany
  • Built an autonomous marketing system using LangGraph and Gemini 2.5 Pro that generates weekly campaign calendars, daily topics, and posting schedules automatically. Cut the team's strategy planning time from days to hours with sub-200ms response times through Redis semantic caching.
  • Designed a dual-pipeline content workflow that separates generation from quality review, using Gemini 2.5 Pro with layered guardrails to catch hallucinations, and Jira + Google Sheets integration to track state. Tripled the marketing team's content output while keeping a human-in-the-loop gate for 100% educational accuracy.
  • Led the architecture of the FIAE Learning Platform (Next.js + Supabase + Drizzle ORM), deployed via Docker on Strato. A multi-role system with RBAC serving trainers, trainees, and management across three vocational programs (FIAE, KfB, KI Manager), used daily across Germany.
  • Created "HAI," the platform's AI assistant, with a three-tier query architecture: Page Indexing for exact PDF retrieval, PGVector with fine-tuned embeddings and RAG for semantic queries, and SQL for deterministic UI operations. Dynamic routing sends each query to the right retrieval strategy. Result: 90%+ of routine support tickets handled automatically, taking real pressure off trainers.
  • Set up the full MLOps lifecycle including drift detection and automated testing, so models stay reliable without constant babysitting.
  • Fine-tuned and served domain-specialized models for regulated fields like tax and legal, running training and inference on local NVIDIA GPUs with CUDA, serving them through NVIDIA Triton, tracking runs and versions in MLflow, and gating each release with an LLM-as-a-Judge evaluation harness.
  • Delivered an on-premises AI assistant for a German tax-advisory client, running on a local, OpenAI-compatible inference gateway so confidential client and tax data never leaves the firm's own network. Full data sovereignty and GDPR alignment, with streaming, document-aware chat and a Next.js front end deployed entirely inside the client's infrastructure.
  • Built an integrated property-management platform for Ataberk Estate, an international real-estate firm, replacing fragmented manual workflows with a central CRM, an AI chatbot for lead qualification, and a real-time communication layer on a fully open-source stack, engineered to cut administrative workload by around 70%.
Software & Data Associate
Dec 2020 - Feb 2024
Cognizant, Pune, India
  • Built ML models (Random Forest, XGBoost) for semiconductor wafer fault detection, handling severe class imbalance with SMOTE and advanced sampling. Reached 87% accuracy validated through k-fold cross-validation, now used for live defect identification in production.
  • Used SHAP values and permutation importance to pinpoint which process variables actually caused manufacturing faults. These findings gave the engineering team concrete targets for improvement, measurably raising quality control benchmarks.
  • Customized Windchill PLM in Java with REST-based backend services, and automated the data pipeline between manufacturing sensors and dashboards, cutting manual data entry by over 60%.
  • Set up CI/CD with GitHub Actions to automate testing and deployment, cutting release cycles and reducing manual QA overhead.
Data Analyst Intern
Jun 2019 - Aug 2019
Leaf Innovations Pvt. Ltd., Delhi, India
  • Built a music recommendation engine using collaborative filtering and market basket analysis, achieving 82% accuracy in predicting user preferences across listening sessions.
  • Created Tableau dashboards that visualized user clusters and listening patterns, helping the product team make data-backed decisions about feature priorities.
Technical Arsenal

Technologies I work with

🧠
AI & Machine Learning
LLMsRAG AI AgentsLangChain LangGraphCrew AI MCPPrompt Engineering GuardrailsModel Evaluation AI GovernanceSemantic Caching Hybrid SearchReranking Fine-Tuned EmbeddingsPGVector NLP
⚡
Languages & Frameworks
PythonTypeScript SQLJava JavaScriptNext.js ReactFastAPI Drizzle ORMTailwind CSS
☁️
Cloud & DevOps
AWSGoogle Cloud Hugging FaceOllama DockerCI/CD GitHub ActionsRedis MLOpsLLMOps MLflowNVIDIA Triton CUDAQdrant SupabaseDrift Detection
📊
Data & Analytics
PyTorchTensorFlow Random ForestXGBoost Scikit-learnPandas NumPyTableau Feature EngineeringData Wrangling PostgreSQLN8n
🛠️
Tools & Workflow
GitJira Agile/ScrumGemini API Claude APIGoogle Sheets API Windchill PLM
Projects

Selected work

Open Source GitHub
Agentic Content Pipeline
Multi-agent content system where three AI agents (Strategist, Writer, Reviewer) collaborate through a LangGraph stateful graph. Includes Redis semantic caching, automatic revision loops, human-in-the-loop approval, and SSE streaming.
LangGraphFastAPIRedisPydantic v2Docker
Open Source GitHub
RAG Hybrid Search Engine
Hybrid retrieval engine combining PGVector dense vectors with BM25 sparse search, fused via Reciprocal Rank Fusion. Features a dynamic query router that automatically picks the optimal retrieval strategy per query.
PGVectorBM25RRFFastAPILangChain
Platform
FIAE Learning Platform
Full-stack apprenticeship management system used daily across three vocational programs in Germany. Trainers manage curricula, trainees track their progress, and company admins oversee everything from a single dashboard.
Next.jsSupabaseDrizzle ORMDockerTypeScript
AI Assistant
HAI: Vocational AI Assistant
An AI assistant built specifically for vocational education. Routes simple lookups through SQL for instant, exact answers, and uses RAG with vector search for open-ended knowledge questions. Handles 90%+ of incoming support queries without human help.
PGVectorRAGHybrid SearchFastAPILLM
Automation
Autonomous Marketing Engine
Replaced the entire manual campaign planning process with an agentic pipeline. Automatically generates weekly marketing calendars with daily topics and posts them via Telegram. What used to take the marketing team a full week now takes hours.
LangGraphGemini 2.5 ProRedisFastAPI
ML Research
Fake News Detection (NLP)
NLP classification pipeline trained on a political dataset that identifies misinformation by analyzing linguistic patterns. Hit 92.82% accuracy with TF-IDF vectorization and passive aggressive classification, with feature importance analysis to make results interpretable and trustworthy.
NLPTF-IDFScikit-learnPython
Predictive Analytics
Lead Score Prediction
Predictive model for X Education that identifies which leads are most likely to convert. Used Recursive Feature Elimination and Variance Inflation Factor analysis to reach ~80% accuracy, sensitivity, and specificity. Found that time on site, lead source, and lead origin were the strongest conversion drivers, enabling targeted marketing strategies that improved engagement.
Logistic RegressionRFEVIF AnalysisPandasPython
Community

Open Source Contributions

24K+

Graphiti by Zep

Bug fix: CLI --host/--port flags were silently ignored in the MCP server configuration
18K+

Google ADK-Python by Google

Bug fix: text artifacts lost .text attribute after GCS round-trip due to serialization asymmetry
20K+

Anthropic Courses by Anthropic

Fix: regex syntax error in Lesson 6.1 grading across all three tutorial variants
28K+

LangGraph by LangChain

CI: unified codespell enforcement across 8 libraries in the monorepo
Independent Work

Ventures & Freelance

Co-Founder & CTO
PawVerse
AI-powered veterinary healthcare platform, live in production, connecting pet owners, clinics, and administrators. I co-founded the company and own the technology end to end: the full stack plus an AI layer for symptom analysis and medical image classification, with vision models fine-tuned on curated datasets.
Node.jsReactMongoDBComputer VisionDocker
Freelance · FamHaus GmbH
TradeOps Agent
End-to-end AI email automation for a German trading company. Connected Microsoft Outlook (Graph API) and Dropbox with an OpenAI agent layer that reads incoming client emails, runs behavior and sentiment analysis, classifies each message by business stage, extracts key data, and auto-drafts context-aware replies in the client's tone. Built draft-only with a human-in-the-loop and full audit logging.
OpenAIMicrosoft GraphDropboxFastAPIPython
Available for Hire
Your Project Could Be Here
I take on freelance projects in AI engineering, agentic systems, workflow automation, and full-stack development. If you have a process that could be smarter or faster, let's talk.
LangGraphFastAPIOpenAIRAGDocker
Education

Academic background

Mar 2024 - Apr 2025

M.Sc in Data Science

University of Europe for Applied Sciences, Potsdam, Germany

Mar 2023 - Nov 2023

Post Graduation in Data Science

International Institute of Information Technology (IIIT), Bangalore, India

2016 - 2020

B.Tech in Information Technology

College of Engineering Roorkee, Roorkee, India

Credentials

Certifications & languages

Nov 2023

Advanced Certification in Data Science

IIIT Bangalore

Nov 2024

Data Science Methodology

IBM

Sep 2024

Machine Learning with Python

IBM

Sep 2024

Python for Data Science

IBM

English
C1 Professional
German
A2 Elementary
Let's Connect

Have a problem AI
could solve? Let's talk.

Whether you need an AI engineer for your team, a freelance consultant to automate your workflows, or just want to exchange ideas, I'm always open to a conversation.

maanik.p.garg@gmail.com +49 15771476289 LinkedIn GitHub