{"$schema":"https://raw.githubusercontent.com/jsonresume/resume-schema/v1.0.0/schema.json","basics":{"name":"Hrishikesh Jadhav","label":"AI Engineer, Germany","image":"https://www.hrishikeshjadhav.com/portrait-v2-560.jpg","email":"knowhrishi.de@gmail.com","url":"https://www.hrishikeshjadhav.com","summary":"AI engineer in Germany with 4+ years shipping production AI and backend systems. I build LLM extraction pipelines, RAG and MCP systems, and the evaluation gates that decide what ships. Open to AI engineering roles in Germany from October 2026. EU Blue Card holder, authorised to work in Germany.","location":{"countryCode":"DE"},"profiles":[{"network":"GitHub","username":"knowhrishi","url":"https://github.com/knowhrishi"},{"network":"LinkedIn","username":"knowhrishi","url":"https://www.linkedin.com/in/knowhrishi"}]},"work":[{"name":"Toku","position":"AI Engineer","location":"Frankfurt / Remote","description":"Global employer-of-record and payroll infrastructure platform operating across 46 countries.","startDate":"2025-10","endDate":"2026-09","highlights":["Shipped AI tooling into daily production across product, engineering and sales teams: an MCP server exposing internal systems to LLM clients, a RAG assistant (FastAPI, LangChain, pgvector), and n8n automations for onboarding, payslip processing and support triage. Owned deployment, documentation, onboarding and hands-on user support.","Cut payroll data intake from hours of manual work per cycle to minutes across production records by building a self-hosted LLM extraction pipeline (Python, FastAPI, PostgreSQL, DigitalOcean) that masks personal data before inference.","Kept field-level extraction accuracy above the agreed threshold across every extracted field, checked against a large golden evaluation set, by building the evaluation harness and a CI regression gate that blocks any deploy below it.","Moved security review to pull-request time across thousands of pull requests by integrating automated LLM-assisted security review into GitHub CI for Toku's financial platform.","Built status.toku.com, Toku's public status platform: production components probed from the Cloudflare edge on a short fixed interval, automated incident detection and resolution, dependency rollups, edge-vs-origin failure isolation, and a JSON API and RSS feed. New incidents notify the team on Slack, and failures that need a code fix are picked up by a coding agent.","Built Toku's customer-facing help centre and AI assistant (toku.com/help, Next.js) on Toku's Notion knowledge base, covering payroll, benefits, policy and country-guide articles across dozens of countries, with general-help and visa-support content in separate retrieval corpora and multi-model fallback across providers.","Brought LLM inference costs down to a fraction of the estimated cost of equivalent third-party API usage by deploying open-weight models on self-hosted GPU infrastructure."]},{"name":"GfK - An NIQ Company","position":"Data Scientist","location":"Nuremberg","startDate":"2022-08","endDate":"2025-09","highlights":["Reduced manual effort in product-taxonomy classification by around 30% by building an LLM classification service on Amazon Bedrock using prompt engineering and RegEx-based post-processing.","Reduced catalogue lookup time by around 40% versus keyword search by building vector-embedding semantic retrieval over internal product catalogues.","Improved simultaneous-viewer prediction accuracy by around 20% over the incumbent model by training and deploying a CatBoost model using 30+ engineered features from sociodemographics, temporal patterns and programme metadata.","Kept production scoring pipelines running 24/7 without manual intervention by orchestrating S3 ingestion, feature generation, model scoring and automated integration tests in GitLab CI/CD, containerised with Docker on Linux.","Built a TV-audience data-fusion pipeline using K-Nearest Neighbors and a genetic algorithm to match and clone panel households against large-scale return-path data."]},{"name":"Sapio Analytics Pvt. Ltd.","position":"Software Developer (Internship)","location":"Mumbai","startDate":"2020-04","endDate":"2020-08","highlights":["Built COVID-19 decision-support models in Python (SEIRD, scikit-learn, SciPy) and forecasting dashboards (Plotly, AWS) used to inform Government of India lockdown and testing-strategy decisions, with a 4.8% RMSE reduction against the prior baseline."]}],"education":[{"institution":"University of Passau","studyType":"M.Sc. Artificial Intelligence Engineering (coursework and thesis)"},{"institution":"University of Passau","studyType":"Honours Degree in Entrepreneurship"},{"institution":"Savitribai Phule Pune University, Pune","studyType":"B.E. Computer Science"}],"awards":[{"title":"NIQ/GfK HACKFEST","date":"2024","summary":"Top 3, with a RAG learning assistant built and demoed in 24 hours"},{"title":"BMW Innovation Challenge","date":"2024","summary":"Selected participant, 24-hour challenge at BMW iFactory Dingolfing (DocCheck use case)"},{"title":"IEEE Machine Learning Hackathon","date":"2020","summary":"1st place"},{"title":"HackCovid-19","date":"2020","summary":"Winner among 130 teams"},{"title":"Smart India Hackathon","date":"2017","summary":"Winner (Ministry of Defence)"}],"publications":[{"name":"Ontology Evolution in Invasion Biology Using Large Language Models: A Hybrid Approach","publisher":"LLM-TEXT2KG 2025, CEUR Workshop Proceedings Vol. 4020, pp. 195-206","releaseDate":"2025","url":"https://ceur-ws.org/Vol-4020/Paper_ID_13.pdf","summary":"A hybrid pipeline that combines GPT-4 prompting and zero-shot extraction with classical ontology engineering to build and evolve INBIO, a core ontology for invasion biology, with domain experts validating new classes."},{"name":"A Deep Learning Mobile Application based Sign Language Recognition for Aphasic Person","publisher":"Journal of Emerging Technologies and Innovative Research (JETIR)","releaseDate":"2021","url":"https://www.jetir.org/view?paper=JETIR2105465","summary":"An Android app that recognises sign-language gestures using Histogram of Oriented Gradients features with CNN and multiclass SVM classifiers."}],"skills":[{"name":"LLM systems and agents","keywords":["LLM application design","RAG","knowledge retrieval","agentic AI","tool calling","MCP servers","structured outputs","prompt engineering","guardrails","LLM evaluation and regression testing"]},{"name":"Models and frameworks","keywords":["LangChain","LangGraph","CrewAI","Claude SDK","OpenAI SDK","Amazon Bedrock","OpenRouter","Hugging Face","open-weight models","Whisper"]},{"name":"Backend and integration","keywords":["Python","TypeScript","Node.js","FastAPI","Flask","Django","Next.js","React","REST API design","API integration","webhooks","OAuth","n8n","workflow orchestration"]},{"name":"Data and retrieval","keywords":["PostgreSQL","Prisma","pgvector","Qdrant","FAISS","Pinecone","vector search","embeddings","data modeling","data pipelines"]},{"name":"Cloud and operations","keywords":["AWS (Bedrock, S3)","GCP","DigitalOcean (self-hosted GPU inference)","Cloudflare","Docker","Linux","Git","GitLab CI/CD","GitHub Actions","Terraform","Kubernetes","observability","production monitoring","incident tooling"]},{"name":"ML and data science","keywords":["PyTorch","scikit-learn","CatBoost","pandas","NumPy","feature engineering","model evaluation"]},{"name":"AI coding tools","keywords":["Claude Code","Cursor"]}],"languages":[{"language":"English","fluency":"C1"},{"language":"German","fluency":"B1"},{"language":"Hindi","fluency":"native"},{"language":"Marathi","fluency":"native"}],"projects":[{"name":"Internal RAG learning assistant","description":"NIQ/GfK HACKFEST 2024, Top 3. Built and demoed a retrieval-augmented learning assistant over internal knowledge within 24 hours, with document retrieval and audio ingestion via Whisper (LangChain, vector database, GPT, FastAPI)."}],"meta":{"canonical":"https://www.hrishikeshjadhav.com/cv.json","version":"v1.0.0"}}