Prajwal Hiremath

Data Scientist

Bengaluru, Karnataka, India5 yrs 4 mos experience

Highly StableAI Enabled

Key Highlights

Architected a multi-tenant AI platform for Pfizer.
Achieved 0.91 AUC in ML predictive pipeline.
Developed a RAG chatbot reducing lookup time by 75%.

Stackforce AI infers this person is a Data Science and AI Engineering expert with a focus on Healthcare and SaaS solutions.

Contact

Skills

Core Skills

Retrieval-augmented Generation (rag)Large Language Models (llm)Machine LearningSoftware Development

Other Skills

PythonFastAPILangGraphAWSDockerPostgreSQLAWS NeptuneDjangoCeleryRedisFlaskPandasOpenAI EmbeddingsDGXNetworking

About

I'm a Data Scientist and AI Engineer with 5 years of experience building AI systems that actually work in production — not just in notebooks. My work sits at the intersection of Agentic AI, RAG architectures, and LLMs. At Deloitte, I architected OmniScout — a multi-tenant AI platform for Pfizer that consolidated 5+ research tools into a single unified system, recognized by leadership for a projected $50M annual benefit and a 30% improvement in experimental success rates for 500+ researchers. Before that, at Cisco, I built the full stack — from a high-availability Django reservation platform handling 5,000+ monthly bookings to an ML predictive pipeline achieving 0.91 AUC, to a RAG chatbot that cut information lookup time by 75%. What I care about is closing the gap between interesting ML research and reliable, production-grade systems. I've worked across the whole pipeline — data engineering, model development, API design, cloud deployment — so I know where things break and how to prevent it. On the technical side, I work primarily with Python, LangGraph, LangChain, CrewAI, FastAPI, AWS (Bedrock, SageMaker, S3), and vector databases like OpenSearch and FAISS. I also hold certifications from NVIDIA, AWS, Microsoft, Google, and Databricks in Generative AI and cloud AI engineering. If you're building something ambitious in the AI/ML space, I'd be glad to connect.

Experience

5 yrs 4 mos

Total Experience

3 yrs 11 mos

Average Tenure

1 yr 5 mos

Current Experience

Deloitte

Data Scientist 2

Jan 2025 – Present · 1 yr 5 mos · Bengaluru · Hybrid

Architected and developed an advanced SQL agent using Langchain and Anthropic Claude on AWS Bedrock, achieving 95% query accuracy and enabling natural language querying of a 7-table relational database.
Engineered a high-precision, multi-agent conversational AI system using a robust pipeline to deconstruct user questions, generate precise SQL queries, and deliver human-readable answers from complex datasets, achieving 99% accuracy.
Developed an intelligent multi-agent RAG system using CrewAI, integrating FAISS vector search, SQL analytics, and web search to serve the pharmaceutical industry, significantly improving research efficiency.
Architected OmniScout, a scalable multi-tenant platform consolidating 5+ domain apps into a unified FastAPI system; recognized by leadership for delivering a projected $50M annual benefit and increasing experimental success rates by 30% for 500+ researchers.
Engineered a production-grade Multi-Agent RAG system using LangGraph and AWS Neptune to orchestrate 5+ specialized agents (Query Analyzer, Tool Orchestrator); implemented streaming responses via SSE with automated inline citations and fact-checking.
Developed a Deep Research Agent and SWOT Analysis workflow for pharmaceutical intelligence, utilizing parallel execution to slash research cycles from hours to minutes while maintaining strict scientific accuracy.
Developed a custom MCP server using FastAPI-MCP to standardize and expose internal tools (such as HR,
DR, and SWOT analytics) as reusable AI capabilities; streamlined tool discovery and cut cross-team deployment cycles by 40% through a unified Model Context Protocol integration.
Designed a YAML-driven prompt orchestration framework and a custom Shifted Context Window algorithm for query optimization; enabled independent tenant workflows and dynamic configuration loading while eliminating code redundancy across teams. Technologies: Python, FastAPI, Pydantic, LangGraph, AWS, Docker, PostgreSQL.

PythonFastAPILangGraphAWSDockerPostgreSQL+2

Cisco

Software Engineer

Jan 2021 – Dec 2024 · 3 yrs 11 mos · Bengaluru · On-site

During my time at Cisco, I independently developed a suite of high-impact data and AI-driven applications to solve critical operational challenges, automate manual workflows, and enhance data-driven decision-making for engineering teams and leadership.
My key projects include:
Testbed Reservation System
Architected a high-availability Django platform scaled to serve 300+ engineers and 5,000+ monthly reservations, eliminating 100% of double-booking race conditions by implementing PostgreSQL row-level locking within atomic transactions.
Engineered a non-blocking Celery-Redis asynchronous notification system and built utilization dashboards, which together reduced testbed idle time by 45% (recovering $150K in annual value). Technologies : Django, PostgreSQL, Celery, Redis, Webex API, VMware.
ML Testbed Predictor
Engineered an ML predictive pipeline to optimize testbed allocation, benchmarking 7+ algorithms; achieved
0.91 AUC using Gradient Boosting, outperforming baseline models by 35% and reducing idle time allocation
failures.
Implemented a robust preprocessing workflow using StandardScaler and LabelEncoder, serializing the pipeline with joblib to prevent training-serving skew; served real-time predictions via a Flask REST API.
Cisco Wiki Analytics Dashboard
Engineered a Flask and Pandas dashboard to automate executive reporting by ingesting, cleaning, and programmatically standardizing raw Excel data, which reduced manual report generation time by 40%.
Delivered hierarchical, interactive chart views tailored for leadership, enabling Directors to see high-level aggregates and Managers to drill-down into specific team/engineer performance for data-driven decision-making. Technologies : Flask, Pandas, HTML, CSS
Testbed Chatbot:
Built a RAG chatbot (FastAPI, OpenAI Embeddings, ChromaDB) that enabled natural language queries for hardware specs, reducing information lookup time by 75%. Technologies : FastAPI, OpenAI Embeddings, ChromaDB