ML Engineer | GenAI & Agentic AI Systems | MLOps

Building production-grade AI systems with focus on Large Language Models, Retrieval-Augmented Generation, and autonomous agent frameworks. Experienced in deploying scalable ML infrastructure from research to production.

• LLM Engineering: Fine-tuning, prompt engineering, and optimization for production use cases
• Retrieval-Augmented Generation (RAG): Advanced RAG architectures with hybrid search, reranking, and query optimization
• Agentic AI: Multi-agent systems with tool use, planning, memory, and orchestration
• Multi-modal AI: Vision-language models, audio processing, and cross-modal applications

• NLP: Transformers, sequence models, semantic search, and information extraction
• Computer Vision: Object detection, segmentation, classification, and visual understanding
• Applied ML: End-to-end pipeline development from data preprocessing to model deployment
• Model Optimization: Quantization, distillation, and efficient inference strategies

• Production Deployment: Containerized model serving with horizontal scaling and load balancing
• CI/CD for ML: Automated testing, validation, and deployment pipelines
• Monitoring & Observability: Metrics, logging, tracing, and drift detection
• Infrastructure as Code: Terraform, Helm charts, and declarative infrastructure management
• Data Engineering: Versioning, lineage tracking, and reproducible workflows

Intelligent Agent Systems

• Multi-agent orchestration with dynamic tool selection and task planning
• Context-aware agents with long-term memory and conversation state management
• Tool-augmented LLMs for code generation, data analysis, and workflow automation

RAG & Knowledge Systems

• Production RAG pipelines with advanced retrieval strategies and semantic chunking
• Hybrid search architectures combining dense and sparse retrieval
• Question-answering systems over structured and unstructured data

End-to-End ML Applications

• Real-time inference APIs with sub-second latency requirements
• Batch processing pipelines for large-scale model predictions
• Computer vision applications for detection, classification, and segmentation

MLOps Infrastructure

• Automated model training, evaluation, and deployment workflows
• Model monitoring with performance tracking and drift detection
• Scalable serving infrastructure with auto-scaling and fault tolerance

• Production LLM Applications: Building reliable, scalable GenAI systems
• Agentic Workflows: Autonomous systems with planning and tool use
• MLOps Best Practices: Reproducible, monitored, and maintainable ML systems
• Research to Production: Bridging the gap between experimentation and deployment
• Clean Architecture: Well-tested, documented, and production-ready code

✅ Reliability: Comprehensive testing, error handling, and graceful degradation
✅ Scalability: Horizontal scaling, caching, and efficient resource utilization
✅ Observability: Detailed logging, metrics, and distributed tracing
✅ Reproducibility: Version control for data, code, and models
✅ Security: API authentication, rate limiting, and secure secret management
✅ Cost Optimization: Right-sizing infrastructure and efficient model serving

Email: reeth_j@ch.iitr.ac.in reethjainrj777@gmail.com
LinkedIn: linkedin.com/in/reeth-jain-rj777

Building AI systems that scale from prototype to production