Job Description

Job Description: About Privy: Privy is India s first consent governance platform, simplifying compliance with the DPDP Act. We are at the cutting edge of privacy tech, AI-driven compliance, and data discovery, enabling businesses to handle PII data, digital journeys, and regulatory processes with intelligence. Our ML team is at the heart of these innovations developing LLM-powered solutions for contract analysis, regulatory compliance, and automated privacy workflows. We build systems that understand contracts, detect dark patterns, classify privacy risks, and automate DPIA responses using both vector-based retrieval (RAG) and structured query approaches. We are looking for a Senior Machine Learning Engineer with expertise in LLMs, NLP, and privacy-focused AI solutions to join our Mumbai team and help shape the future of AI-powered data protection. Why Join Us Be at the forefront of privacy AI solving real-world compliance challenges using cutting-edge AI. Work on challenging AI problems in contract analysis, PII classification, and regulatory automation. Collaborate with top legal, compliance, and AI researchers. Competitive salary, flexible work culture, and a high-impact role in a fast-growing privacy tech company. Do check out more of the stuff we do: IDfyU (Candidate page): https: / / sites.google.com / idfy.com / idfyu / home Instagram: https: / / www.instagram.com / we.are.idfy / LinkedIn: https: / / www.linkedin.com / company / idfy / IDfy Website: https://www.idfy.com/ Experience Range: 4 - 8 years Educational Qualifications: B.Tech/B.E Job Responsibilities: In this role you will: Develop and fine-tune LLMs for contract analysis, regulatory classification, and risk assessment. Implement Retrieval-Augmented Generation (RAG) using vector embeddings and hybrid DB-based querying to power DPIA and compliance workflows. Build AI-driven contract analysis systems to detect dark patterns, classify clauses, and provide remediation suggestions. Develop knowledge graph-based purpose taxonomies for privacy policies and PII classification. Automate data discovery for structured and unstructured data, classifying it into PII categories. Optimize sliding window chunking, token-efficient parsing, and context-aware summarization for legal and compliance texts. Build APIs and ML services for deploying models in a high-availability production environment. Collaborate with privacy, legal, and compliance teams to build AI solutions that power Privy s data governance tools. Stay ahead of the curve with agentic RAG, multi-modal LLMs, and self-improving models in the compliance domain. Skills Required: LLM , RAG , AgenticAI , NLP , Python , Problem solving Candidate Attributes: Must-Have Skills 3-5 years of experience in Machine Learning, NLP, and LLM-based solutions. Strong expertise in fine-tuning and deploying LLMs (GPT-4, Llama, Mistral, or custom models). Experience with RAG-based architectures, including vector embeddings (FAISS, ChromaDB, Weaviate, Pinecone, or similar). Hands-on with agentic RAG, sliding window chunking, and efficient context retrieval techniques. Deep understanding of privacy AI use cases, including contract analysis, regulatory classification, and PII mapping. Proficiency in Python and frameworks like PyTorch, TensorFlow, JAX, Hugging Face, or LangChain. Experience in building scalable AI APIs and microservices. Exposure to MLOps practices, including model monitoring, inference optimization, and API scalability. Experience working with at least one cloud provider (AWS, GCP, or Azure). Good-to-Have Skills Experience in hybrid AI architectures combining vector search + relational databases. Familiarity with functional programming languages (Go, Elixir, Rust, etc.). Understanding of privacy compliance frameworks (DPDP Act, GDPR, CCPA, ISO 27701). Exposure to Kubernetes, Docker, and ML deployment best practices. Contributions to open-source LLM projects or privacy AI research. Job Code: KL-P6SP9MHR