Hi, I'm Mohith Doddapaneni
AI Engineer with around two years of professional experience in AI projects, automation, and digital transformation at Yara International. Experienced in requirements gathering, feasibility studies, implementation, documentation, and stakeholder communication. Specialised in Generative AI, Agentic AI, LLM engineering, and process improvement. Currently pursuing an M.Sc. in Applied AI at Deggendorf Institute of Technology, Germany. Organised, responsible, and a strong team player with excellent English skills (C1).
Turning ideas into digital reality
AI Engineer with around two years of professional experience in AI projects, automation, and digital transformation at Yara International. Experienced in requirements gathering, feasibility studies, implementation, documentation, and stakeholder communication. Specialised in Generative AI, Agentic AI, LLM engineering, and process improvement. Currently pursuing an M.Sc. in Applied AI at Deggendorf Institute of Technology, Germany. Organised, responsible, and a strong team player with excellent English skills (C1).
Projects I've Built
A selection of projects that showcase my skills and experience
Enterprise RAG Pipeline
Production-grade hybrid retrieval-augmented generation system
Enterprise knowledge bases contain thousands of PDFs and documents that are inaccessible to natural language queries. Built a production-grade RAG system that ingests documents, retrieves the most relevant context, and generates grounded, source-attributed answers.
Hybrid retrieval combining dense vector search (ChromaDB) and sparse BM25 via Reciprocal Rank Fusion, with …
Multi-Agent Research System
LangGraph-based autonomous multi-agent research pipeline
Complex research tasks require planning, web research, analysis, writing, and quality review — sequential steps that a single LLM call handles poorly. Orchestrated multiple specialised AI agents that collaborate on a research task and self-correct until the output meets a quality threshold.
LangGraph StateGraph with five specialised agents (Planner, Researcher, Analyst, Writer, Critic) with condi…
LLM Fine-tuning Pipeline
QLoRA fine-tuning of Phi-2 on custom instruction dataset with streaming inference
Full fine-tuning of large language models requires 80 GB+ VRAM and significant compute cost. Applied QLoRA to fine-tune Phi-2 (2.7B) on a custom instruction dataset using a free GPU (Colab T4) and served it with streaming inference.
QLoRA with 4-bit NF4 quantisation reducing VRAM from ~12 GB to ~6 GB, LoRA adapter matrices, TRL SFTTrainer…
Technical Proficiency
Technologies and tools I work with to bring ideas to life
LLM Engineering
Agentic AI
Generative AI
Frameworks & APIs
Data & Cloud
Databases & Storage
Work Experience
My professional journey and the impact I've made
Associate Engineer – AI & Data
Supported execution, coordination, and documentation of AI and digitalisation projects. Deployed a GPT-3.5-powered conversational knowledge platform on Azure. Built CNN image analysis model (80% accuracy) and NLP pipeline in production. Prepared Power BI dashboards and decision documents for management.
- ▸Deployed GPT-3.5 conversational knowledge platform on Azure across five business teams
- ▸Built CNN image analysis model achieving 80% accuracy — end-to-end from data to deployed output
- ▸Contributed to PoC development for AI use cases: scoping, feasibility, prototyping, stakeholder assessment
Intern – Process Automation
Built Power Apps and Power Automate solutions for IT service management. Worked independently with requirements, build, test, and documentation. Communicated proactively with stakeholders throughout.
- ▸Independently built Power Apps and Power Automate solutions for IT service management
- ▸Delivered requirements, build, test, and documentation in a structured, self-directed manner
Let's Work Together
Have a project in mind? Let's discuss how I can help bring your ideas to life.
Get in touch
Location
Deggendorf, Germany