Experience
Master Thesis
Smart City Research Lab
From Crude to Crafted: Refining Participatory Design Data into Stakeholder-Ready Outcomes
- Architected a production Document AI platform using Retrieval Augmented Generation (RAG) over 1,500+ participatory design artefacts to answer historical project queries with grounded responses.
- Designed LLM evaluation combining RAGAS, custom evaluation metrics and human-in-the-loop (HITL) validation workflows to evaluate factual grounding, response quality, and prompt performance.
- Built a React, TypeScript, and D3.js frontend for interactive exploration of AI-generated insights.
- Implemented input layer LLM safety controls and Guardrails, including PII redaction and foul language filtering.
Machine Learning Engineer
Flashcloud software private limited
Client: Food Delivery Startup
- Developed machine learning demand forecasting models reducing forecast error (MAPE) by 7% and improving driver allocation and capacity planning.
- Developed and deployed an LSTM based text classification model exposed through Flask REST APIs, improving customer feedback classification accuracy by 13% over baseline models and automating issue routing.
Client: SAHU & ASSOCIATES, Chartered Accountants
- Developed a Document AI pipeline using BERT based Named Entity Recognition (NER) models to extract structured JSON from insurance claims and invoices.
- Developed an internal ML tool to identify anomalous financial patterns across small scale industries, helping Chartered Accountants prioritize audits and investigate high risk companies.
Cross Project Contributions
- Deployed and maintained production ML inference services using Docker and Kubernetes, integrating with automated retraining workflows orchestrated through Airflow.
- Implemented experiment tracking with MLflow to log training metrics and parameters, compare model performance, and support model selection and reproducible ML development.
- Designed lightweight model serving APIs using Flask and Gunicorn (WSGI) reducing inference latency to sub-100 ms while decoupling ML inference from the primary application for independent deployment and scaling.
- Monitored production ML inference services by validating data quality and detecting schema and performance drift.
AI Agent Hackathon - HackerRank Orchestrate
- Built a multimodal agentic router with Google ADK to classify WhatsApp messages as notify, digest, or mute using contextual tool calls.
- Implemented RAG based retrieval, Gemini vision/OCR, ASR (conversational AI) and image deduplication for grounded multimodal message analysis.
- Pydantic schemas, deterministic fallbacks, checkpointing, retries and 90+ unit tests for reliable end-to-end execution.
AI Automotive Voice Agent
- Built real-time voice agent for automotive sales/service using WebRTC, supporting vehicle search, CRM capture and appointment booking.
- Exposed 11 agent tools via n8n MCP, enforcing IDs, opening hours, booking conflicts and workshop capacity at the tool boundary.
- Reduced LLM TTFT from 3.0s to 0.5s via LiteLLM routing and model benchmarking; selected Gemini 2.5 Flash for latency and tool call reliability.
- Enforced tool grounded responses and structured failures, preventing hallucinated bookings; automated reproducible n8n setup with Python/REST API scripts.
MarketLens - multi agent Indian equity (NSE/BSE) analysis system
- Built 4 agents working in parallel (technical, news sentiment, sector rotation, derivatives) using LangGraph and DeepSeek V4 Flash, each with isolated context windows to preserve reasoning quality.
- Implemented agent execution workflows with structured state transitions, context management, and failure handling.
- Implemented agent execution tracing to capture planning steps, tool invocations, intermediate reasoning states, and final outputs for debugging and analysis.
Industry experience
See where this freelancer has spent most of their professional time.
Experienced in Information Technology, Food and Beverage, Insurance, and Professional Services.
Business area experience
See which departments and functions this freelancer has contributed to most.
Experienced in Information Technology, Audit, Business Intelligence, Customer Service, Finance, and Operations.
Frequently asked questions
Have questions? Find more information here.
Prajwal is based in Bamberg, Germany.
Prajwal speaks the following languages: English (Advanced), German (Elementary).
Prajwal has at least 3 years of experience. During this time, Prajwal has worked in at least 2 different roles and for 2 different companies. The average length of individual experience is 2 years and 6 months. Note that Prajwal may not have shared all experience and actually has more experience.
Based on recent experience, Prajwal would be well-suited for roles such as: Master Thesis, Machine Learning Engineer, AI Agent Hackathon - HackerRank Orchestrate.
Prajwal's most recent position is Master Thesis at Smart City Research Lab.
In recent years, Prajwal has worked for Smart City Research Lab and Flashcloud software private limited.
Prajwal is most experienced in industries like Information Technology, Food and Beverage, and Insurance. Prajwal also has some experience in Professional Services.
Prajwal is most experienced in business areas like Information Technology, Audit, and Business Intelligence. Prajwal also has some experience in Customer Service, Finance, and Operations.
Prajwal holds a Master in International Software System Science from Otto-Friedrich University Bamberg.
Prajwal has 2 certificates. These include: NVIDIA Certified Associate and Oracle Cloud Infrastructure 2025 Certified Generative AI Professional.
The availability of Prajwal needs to be confirmed.
Daily rate distribution
The rates shown represent the typical market range for freelancers in this position based on recent contracts on our platform.
Average rates for similar positions
Rates are based on recent contracts and do not include FRATCH margin.
The average daily rate is the mean of all daily rates from recent contracts of comparable freelancers on our platform.
The median daily rate is the middle value of all daily rates — half of comparable freelancers charge less, half charge more. Unlike the average, it is barely affected by outliers.
Calculated based on our freelancers’ daily rates as of 18 Nov 2026. Actual rates may vary depending on seniority level, experience, skill specialization, project complexity, and engagement length.
Similar freelancers
Discover other experts with similar qualifications and experience
Patrick L.
Last position:
Senior GenAI Fullstack Developer at SBH (Schulbau Hamburg)
Remote freelance role focused on Agentic AI strategy, secure application patterns, and reusable agentic workflows for a government agency.
- Development and implementation of an open-source Agentic AI strategy for a government agency, with a focus on GDPR, security, and self-hosted solutions
- Development of reusable agentic workflows and business applications that enable non-technical employees to solve business problems independently
- Implementation of nine business applications with Single Sign-On (SSO) and Azure PostgreSQL integration on Hetzner Linux servers
Techstack: Python, Streamlit, Anthropic SDK (Claude), Azure, Linux, PostgreSQL, MS SQL, Angular
Ralph N.
Last position:
AI Lead Engineer Car Configurator for leading German premium manufacturer at e-ntegration GmbH
- Intent-driven approach to configure all models across all series automotive in all distribution markets of this car manufacturer
- Developed a customer-facing, conversation-driven integration layer to achieve 100% hallucination-free technical configurations
- Utilized Microsoft Azure AI Services: AI Foundry, Agent Service, AI Search; Prompt Shield Services; Content Security; Terraform; API Gateway; AI Gateway; Container Services; Azure Agent SDK; Agent Skills; RAG; MCP Servers and tools
Daniel S.
Last position:
AI Strategy & Use-Case Development at Umwelt Service Salzburg
- AI strategy concept and implementation roadmap for an energy consulting company.
- Use-case matrix with nine application scenarios (including funding research, chatbot, initial AI consulting, topic radar), implemented as reusable Claude Code skills.
- AI strategy, use-case analysis / Claude Code Skills / n8n.
Martin M.
Last position:
Product Owner AI Learning Platform at B2B Tech Scale-Up
- Agile development of a multimodal analysis platform for training materials (video, audio, documents) using Scrum
- Extraction of context-relevant content based on user profiles & competency dimensions
- Personalized delivery of learning content to improve sales performance
- Close coordination with sales teams & stakeholders to validate features
- Use of Gemini, Whisper, Python & JavaScript, deployment on AWS, Perl for scripting data imports
- Integration into existing tools & CRM systems for smooth adoption
- Technologies used: Python, OpenAI, DB tech such as PostgreSQL, CI/CD for AirFlow DAGs, FastAPI
Viktor S.
Last position:
AI Engineer (Freelance) at Empion
Enterprise AI content categorization and AI-powered web research.
- Built multi-LLM evaluation framework with annotated data
- Iterated LLM error rates based on annotated datasets
- Implemented AI-powered web research pipeline Stack: LLM, evals, OpenRouter, Python, Node.js, TypeScript, React
Stefan O.
Last position:
Founder at ProtocolEngine.io
Evidence-led health intelligence platform turning published research into personal health protocols. It scores 430 habits, foods, and supplements against the studies behind them, and moves the score when the evidence moves. Built solo.
- Built the daily ingestion pipeline across PubMed, bioRxiv, and medRxiv: 43,000+ papers from 3,400+ journals processed into 230,000+ typed evidence claims, each one traceable back to the study it came from.
- Designed the six-factor evidence scoring model and the public changelog behind it, so no recommendation ever appears without the papers underneath it. 23,000+ grade changes recorded and explained to date.
- Shipped an entity information model connecting every intervention to its mechanisms, biomarkers, and outcomes: 118 biomarkers with region-specific reference ranges, 77 mechanisms, 32 graded outcomes.
- Built the personalisation layer: blood panel ingestion that reads lab PDFs with a vision model and corrects results for draw time against the user's wake anchor, plus Oura, WHOOP, and Withings integration for daily readiness context.
- Operate eleven specialised review agents over the corpus and codebase, covering paper curation, retrieval quality, health-claim compliance across EU and US regimes, and security.
- Shipped the Evidence Assistant, a RAG assistant that answers from the claim database and cites the underlying papers, plus a B2B practitioner tier, an Expo React Native app, and localisation across 3 languages and 7 markets.
Stack: Next.js 16, TypeScript, Supabase, pgvector, Anthropic Claude, Vercel, DeepInfra.
Experts recently working on similar projects
Freelancers with hands-on experience in comparable project as a Master Thesis
Nearby freelancers
Professionals working in or nearby Bamberg, Germany
