PhD in Machine Learning
VIT, Vellore · 2020 · GPA 9/10
Completed doctoral research on rumor detection and control with deep learning.
Dr. Santhoshkumar
Senior Machine Learning Engineer | Enterprise AI Systems & Platforms
I design and deliver production-grade AI systems that improve customer experience while reducing operational costs.
At Eurowings (Lufthansa Group), I lead the design and delivery of AI platforms—from ambiguous business problems to reliable, monitored production systems.
Highlights
- Reduced customer support calls by 18%
- Improved search satisfaction by 45%
- Reduced ML deployment cycles from weeks to hours
- Specialized in Semantic Search, RAG, LLM Applications and Enterprise MLOps
Agentic AILLM SystemsML SystemsSemantic SearchProduction MLOpsDatabricksAzure
Eurowings Digital GmbH • Europe | Remote
Production AI Leadership
Senior ML Engineer / Data Scientist
Current Focus
Search, LLMs, and MLOps
Production
13+
Years
2012-2016: Backend (Java) Engineering → Team Lead
2016-2020: PhD (ML) + Team Leadership
2020-2026: Enterprise AI Systems at scale in Lufthansa Group
4
Featured Production Systems
Recent flagship projects: Search, RAG, MLOps, Forecasting. 10K QPS, 2M embeddings, 40ms P99 latency.
Proven Impact
- 18% support call reduction = $420K annual savings
- 45% search satisfaction improvement (62% → 90%)
- 98% deployment time reduction (weeks → hours)
About
Most AI prototypes never become successful products. My passion is turning innovative ideas into reliable production systems.
I design and deliver production-grade AI solutions that transform complex business problems into measurable outcomes. With 13+ years of industry experience spanning software engineering, machine learning, and AI systems, and a Ph.D. in Machine Learning, I specialize in developing enterprise AI platforms including semantic search, retrieval-augmented generation (RAG), forecasting solutions, and MLOps systems that improve customer experience while operating reliably at scale.
My background in backend engineering, technical leadership, applied machine learning, and research enables me to bridge the gap between experimentation and production. I build AI solutions that balance model performance, retrieval quality, latency, scalability, governance, and operational cost to create systems that deliver sustained business value.
I enjoy solving the complete AI lifecycle—from data exploration and model development to deployment, monitoring, evaluation, and continuous improvement—because successful AI is not just about building accurate models; it is about building systems that work reliably in the real world.
Engineering Philosophy
I believe successful AI products are built through engineering discipline rather than larger models.
My design principles are:
- 1Retrieval quality before prompt engineering
- 2Measure before optimizing
- 3Reliability over novelty
- 4Simple systems outperform complex systems in production
- 5Evaluation should drive every deployment decision
My goal is to build AI systems that engineers can confidently operate and customers can trust.
Enterprise AI Systems
Production AI systems built for enterprise scale. From search to RAG to MLOps infrastructure.
Leadership & Delivery
- Technical lead for enterprise AI initiatives involving product managers, software engineers, data scientists, and business stakeholders.
- Designed end-to-end AI architectures from requirements gathering through production deployment and monitoring.
- Standardized reusable MLOps patterns using Azure Databricks and MLflow to accelerate ML delivery.
- Collaborated across engineering and business teams to translate customer problems into production AI solutions.
- Mentored engineers on production ML practices, evaluation methodologies, and system design.
Note: Leadership responsibilities listed above reflect technical leadership and cross-functional collaboration. Direct people management responsibilities are documented in individual project ownership sections.
Open Source & Engineering
Experimentation, tooling, and data engineering projects demonstrating breadth and curiosity.
More projects on GitHub
Currently Exploring
Staying current with emerging AI patterns and infrastructure
🤖Agentic AI
📊AI Evaluation Frameworks
🔌MCP Servers
📚Long-context RAG
🏗️LLM System Design
🎯Retrieval Benchmarks
Impact at Scale
Production systems, measurable outcomes, and engineering ownership across search, LLM applications, and platform delivery.
13+
Years Experience
4
Production AI Systems
3
LLM Applications
Enterprise
MLOps Projects
Leadership and Credibility
Senior-level signals from career progression, doctoral depth, and enterprise ownership.
10+ Years Team Leadership
From Software Teams to ML Teams · 2016-Present
Led software delivery teams (2016-2020), then transitioned to leading ML engineering teams—[cross-functional teams] building production AI systems (2020-present).
13+ Years in Industry
From Java/AEM to Production AI
Progressed from enterprise software engineering to ownership of production AI systems.
Selected Production Initiatives
Four production systems that show how I work across retrieval, LLM applications, platform engineering, and applied machine learning.
4-month production rollout
AI-Powered Semantic Search
Eurowings · Lufthansa Group
- •Keyword-only search caused poor retrieval for natural-language questions, multilingual queries, and support intent inside booking journeys.
- •18% reduction in customer support calls
- •45% increase in search satisfaction
Semantic SearchRAGVector SearchGPT-4LlamaIndex
3-month production rollout
Enterprise AI Customer Support
Eurowings · Lufthansa Group
- •Customers repeatedly asked about baggage, cancellations, refunds, check-in, and special assistance, overloading support channels.
- •Reduced repetitive support workload
- •Improved first-response speed
RAGGPT-4LlamaIndexConversational AIAzure
6-month platform build
Enterprise MLOps Platform
Eurowings · Lufthansa Group
- •Teams deployed models inconsistently, with weak governance, fragmented monitoring, and no reproducible delivery path.
- •Reduced deployment time from weeks to hours
- •Standardized delivery across ML teams
MLOpsDatabricksMLflowUnity CatalogAzure DevOps
5-month production rollout
AI Forecasting & Personalization
Eurowings · Lufthansa Group
- •Manual forecasting and non-personalized campaigns created planning inefficiencies and weaker customer targeting.
- •Improved forecast accuracy for planning workflows
- •Raised campaign targeting quality
XGBoostProphetCollaborative FilteringTime Series
2-month experimentation
AI Search Agent
Open Source
- •Traditional search engines return documents, but users increasingly expect conversational answers and autonomous task execution requiring multi-step reasoning.
- •Demonstrates modern Agentic AI design patterns
- •Provides foundation for enterprise search assistants
AI AgentsSemantic SearchTool CallingLangChainGPT-4
Speaking and Credentials
Teaching, invited talks, and certifications that reinforce technical leadership.
International Faculty Development Program (6-days)
Gopalan College of Engineering and Management (GCEM) • 2025-02-03 to 2025-02-08 • Bengaluru, India
Delivered NLP and data science sessions for faculty, with research directions and live demos.
Guest Lecture on Professional Software Development Using Java
School of Information Technology and Engineering • 2020-02-05 • VIT, Vellore
Presented software engineering process, tools, and applied Java practices.
Conference Proceedings talk on Rumor Control
INDIA-2018 • 2018-07-20 • Mauritius
Presented pulse-vaccination based rumor control research.
Tech Stack
Capabilities organized by system responsibility rather than a flat keyword list.
Generative AI & LLMs
GPT-4Azure OpenAILlamaIndexLangChainRAGPrompt EngineeringVector SearchSemantic Search
ML Engineering
PythonPyTorchTensorFlowScikit-learnXGBoostMLflowModel Serving
MLOps & Platform
DatabricksAzure MLDockerKubernetesCI/CDModel MonitoringUnity Catalog
Data & Search
Vector DatabasesAzure AI SearchElasticsearchSQLNoSQLData Pipelines
Cloud & Infrastructure
AzureAWSFastAPIREST APIsMicroservices
Latest Writing
Engineering judgement from production search, enterprise AI delivery, and retrieval system design.
Selected Publications
Optional reading for deeper technical context and academic work.
2019
International Journal on Semantic Web and Information Systems (IJSWIS)
A Parallel Neural Network approach for Faster Rumor Identification in Online Social Networks
CNN architecture for early rumor identification.
View publication2020
Journal of Organizational and End User Computing
A Bio-inspired Defensive Rumor Confinement Strategy in Online Social Networks
Bio-inspired strategy for rumor containment.
View publication2020
International Journal of Web Services Research (IJWSR)
A Neuro-Fuzzy approach to detect Rumors in Online Social Networks
Hybrid neuro-fuzzy model for rumor detection.
View publication2019
SN Applied Sciences (Springer)
Interest Aware Influential Information Disseminators in Social Networks
Influence modeling for targeted information diffusion.
View publication2019
Information Systems Design and Intelligent Applications (Springer)
An Effective Rumor Control Approach for Online Social Networks
Pulse-vaccination inspired rumor control strategy.
View publicationInterested in building reliable AI systems?
I'm always happy to discuss Enterprise AI, Search, RAG, MLOps, and Production Machine Learning.
Let's connect.
santhoshramuk@gmail.com • Europe | Remote