Machine Learning Engineer - 2

• Design, develop, and own production-grade ML/AI systems across the complete development lifecycle.

• Design, develop, and own production-grade ML/AI systems across the complete development lifecycle.
• Build and integrate LLM-powered applications , including RAG pipelines, conversational AI, and agentic workflows.
• Develop retrieval systems using embeddings, vector search, semantic retrieval, and context enrichment .
• Build AI capabilities for personalization, memory, recommendations, and user intelligence .
• Design LLM orchestration workflows to coordinate models, tools, retrieval systems, and application logic.
• Develop evaluation frameworks to measure LLM quality, accuracy, relevance, reliability, latency, and cost .
• Optimize AI systems for production performance, scalability, response quality, and resource efficiency.
• Combine structured domain intelligence with ML, retrieval, and LLM reasoning to deliver context-aware outputs.
• Build and maintain APIs and production services that integrate AI capabilities with backend systems.
• Design scalable ML/AI architectures suitable for high-volume production environments.
• Develop experiments, prototypes, and proof-of-concepts and transition successful solutions into production.
• Implement monitoring, evaluation, debugging, and continuous improvement processes for deployed AI systems.
• Collaborate with Product, Backend, and cross-functional engineering teams to deliver AI-powered features.
• Evaluate emerging LLMs, open-source models, retrieval techniques, agent frameworks, and AI tooling .
• Contribute to engineering standards, technical documentation, model evaluation practices, and AI system design.
• Take ownership of problems end-to-end, from design and implementation through evaluation, deployment, and production support .

• 3+ years of experience in Machine Learning, Applied ML, NLP, Generative AI, or AI engineering.
• Strong proficiency in Python with solid software engineering and programming fundamentals.
• Hands-on experience building applications using LLMs, RAG, embeddings, vector search, or conversational AI .
• Proven experience deploying and supporting ML/AI systems in production .
• Strong understanding of machine learning fundamentals, model evaluation, experimentation, and performance optimization.
• Experience designing and developing AI APIs, scalable services, and production-ready systems .
• Strong understanding of system design, scalability, reliability, and cloud-based application development.
• Experience evaluating and optimizing LLM applications for quality, latency, cost, and reliability .
• Strong understanding of retrieval pipelines, prompt engineering, context management, and LLM orchestration.
• Ability to independently own technical problems across the complete lifecycle: design → build → evaluate → deploy → improve .
• Experience with LangChain or LangGraph is an advantage.
• Familiarity with vector databases and technologies such as Pinecone, Weaviate, Milvus, pgvector, or similar is desirable.
• Experience with Hugging Face and open-source LLMs is a plus.
• Knowledge of MLOps, LLM evaluation frameworks, recommendation systems, or multilingual/Indic NLP is an advantage.
• Strong analytical and problem-solving skills with a practical, experimentation-driven approach.
• Excellent communication and collaboration skills with the ability to work effectively across Product and Engineering teams.
• Strong ownership mindset and interest in building reliable, scalable, and user-focused AI products.