Machine Learning Engineer – NLP, RAG & Generative AI

We are looking for a Machine Learning Engineer (3+ years) to build production-grade NLP systems, optimized search engines, RAG pipelines, and AI-driven automation using both traditional Machine Learning and Generative AI.

This role requires hands-on experience in applying vector embeddings, LLMs, and Python-based systems to solve complex, real-world business workflows efficiently and at scale.

Experience: 3+ Years

• Develop and optimize NLP/ML models (text classification, NER, domain-specific pipelines).
• Build LLM-powered information extraction and document understanding systems.
• Design vector embeddingbased systems for:
• Semantic and hybrid search
• Document similarity, clustering, and deduplication
• Intelligent routing and workflow automation
• Design and implement RAG pipelines , including:
• Document chunking strategies
• Embedding generation, retrieval, and ranking
• Prompt construction with retrieved context
• Build optimized search engines using hybrid approaches (keyword + vector search).
• Work with vector databases (FAISS, Pinecone, Weaviate, Chroma, etc.).
• Develop LLM-powered applications such as document chat, Q&A, summarization, and extraction.
• Integrate multiple LLM providers (OpenAI, Azure OpenAI, Hugging Face).
• Optimize token usage, latency, and cost in LLM-based systems.
• Build AI agents and intelligent automation workflows using LLMs, embeddings, and decision logic.
• Develop scalable Python APIs and services and support production deployments.

• 3+ years of experience in Machine Learning, NLP, and Python development .
• Strong understanding of ML fundamentals and evaluation techniques .
• Hands-on experience with:
• scikit-learn, PyTorch or TensorFlow
• spaCy / NLTK / Hugging Face
• Practical experience with:
• Vector embeddings and semantic similarity
• RAG architectures
• Hybrid search systems (keyword + vector)
• Experience working with vector databases .
• Hands-on experience with LangChain, LangGraph, LlamaIndex, or AutoGen .
• Experience building LLM-powered information extraction systems.
• Experience optimizing LLM prompts, token usage, latency, and cost .
• Experience handling domain-specific or scientific text data .
• Strong problem-solving and production-oriented mindset.

• Familiarity with Agentic AI architectures .
• Experience with cloud platforms (AWS / Azure / GCP).
• Exposure to Docker, CI/CD, and model monitoring .

• Build real, production-scale GenAI systems
• Work across traditional ML, RAG, and agentic AI
• Design optimized, cost-aware AI architectures
• Clear growth path into senior and technical leadership roles