Machine Learning Engineer

You will be responsible for building and deploying scalable LLM-based systems using technologies such as OpenAI, Claude, LLaMA, or Mistral for contract understanding and legal automation. Additionally, you will design and implement Retrieval-Augmented Generation (RAG) pipelines utilizing vector databases like FAISS, Pinecone, and Weaviate. Your role will involve fine-tuning and evaluating foundation models for domain-specific tasks such as clause extraction, dispute classification, and document QA. Furthermore, you will be expected to create recommendation models that offer suggestions for similar legal cases, past dispute patterns, or clause templates through collaborative and content-based filtering. Developing inference-ready APIs and backend microservices using FastAPI/Flask and integrating them into production workflows will also be part of your responsibilities. You will need to optimize model latency, prompt engineering, caching strategies, and accuracy using A/B testing and hallucination checks. Collaboration with Data Engineers and QA team members to convert ML prototypes into production-ready pipelines will be essential. Continuous error analysis, evaluation metric design (F1, BLEU, Recall@K), and prompt iterations will also fall under your purview. Participation in model versioning, logging, and reproducibility tracking using tools like MLflow or LangSmith is expected. Additionally, staying up-to-date with research on GenAI, prompting techniques, LLM compression, and RAG design patterns will be crucial. Qualifications: - Bachelors or Masters degree in Computer Science, AI, Data Science, or a related field. - 2+ years of experience in applied ML/NLP projects with real-world deployments. - Experience with LLMs like GPT, Claude, Gemini, Mistral, and techniques like fine-tuning, few-shot prompting, and context window optimization. - Strong knowledge of Python, PyTorch, Transformers, LangChain, and embedding models. - Hands-on experience integrating vector stores and building RAG pipelines. - Understanding of NLP techniques such as summarization, token classification, document ranking, and conversational QA. - Bonus: Experience with Neo4j, recommendation systems, or graph embeddings.,