๐ง๐ต๐ถ๐ ๐ฟ๐ผ๐น๐ฒ ๐ถ๐ ๐ณ๐ผ๐ฟ ๐ผ๐ป๐ฒ ๐ผ๐ณ ๐๐ต๐ฒ ๐ช๐ฒ๐ฒ๐ธ๐ฑ๐ฎ๐'๐ ๐ฐ๐น๐ถ๐ฒ๐ป๐๐ ๐ฆ๐ฎ๐น๐ฎ๐ฟ๐ ๐ฟ๐ฎ๐ป๐ด๐ฒ: ๐ฅ๐ ๐ฏ๐ฌ๐ฌ๐ฌ๐ฌ๐ฌ๐ฌ - ๐ฅ๐ ๐ฐ๐ฌ๐ฌ๐ฌ๐ฌ๐ฌ๐ฌ (๐ถ๐ฒ ๐๐ก๐ฅ ๐ฏ๐ฌ-๐ฐ๐ฌ ๐๐ฃ๐) Experience: 3+ yrs Location: Bengaluru We are looking for a skilled and innovative AI/ML Engineer to build and scale intelligent AI systems focused on Large Language Models (LLMs), conversational AI, long-term memory, and personalization. The role involves developing advanced retrieval systems, adapting open-source models, and building domain-specific AI capabilities that deliver context-aware, accurate, and personalized user experiences. The ideal candidate will combine strong Python programming skills with hands-on expertise in LLM engineering, Retrieval-Augmented Generation (RAG), vector databases, model fine-tuning, and production deployment. Requirements Key Responsibilities โข Design and develop conversational AI systems with contextual understanding, long-term memory, and personalised response generation. โข Build and optimise RAG pipelines using embeddings, vector databases, structured data, and knowledge retrieval techniques. โข Develop memory systems for user profiling, information extraction, relevance scoring, retrieval, ranking, and context selection. โข Integrate, deploy, and fine-tune open-source LLMs for specific product and domain requirements. โข Develop specialised Small Language Models (SLMs) to support domain-specific reasoning and improve response quality. โข Create domain-specific datasets and training pipelines for fine-tuning, model adaptation, and continuous learning. โข Implement LLM orchestration, prompt engineering, classification, ranking, and lightweight machine learning workflows. โข Build evaluation frameworks to measure retrieval relevance, memory accuracy, reasoning quality, response consistency, and overall model performance. โข Optimise inference latency, compute utilisation, model reliability, and deployment costs. โข Develop and maintain model-serving APIs, automated tests, monitoring systems, and production deployment workflows. โข Investigate AI failures, analyse model outputs, and implement improvements based on measurable performance indicators. โข Collaborate with Product and Engineering teams to translate user requirements into scalable AI solutions. โข Evaluate emerging LLM technologies, retrieval architectures, and model optimisation techniques to improve system capabilities. What Makes You a Great Fit โข 3+ years of experience in AI/ML engineering, machine learning, NLP, or production AI application development. โข Strong proficiency in Python and experience building reliable, production-grade AI systems. โข Hands-on experience with LLMs, open-source models, embeddings, vector databases, and RAG architectures. โข Understanding of LLM fine-tuning, dataset preparation, model evaluation, and inference optimisation. โข Experience developing retrieval, conversational memory, context management, or personalisation systems. โข Familiarity with LLM orchestration frameworks, prompt engineering, and multi-step AI pipelines. โข Experience deploying models through APIs and implementing testing, monitoring, and production support. โข Strong analytical and problem-solving skills, with the ability to evaluate AI improvements using measurable outcomes. โข Knowledge of LoRA/QLoRA, SLMs, knowledge graphs, Neo4j, or graph-based retrieval is an advantage. โข Experience with recommendation systems, ranking models, synthetic data generation, or automated evaluation pipelines is beneficial. โข Familiarity with GPU inference optimisation and self-hosted open-source models is desirable. โข Experience in astrology, symbolic reasoning, or specialised domain-reasoning systems is an added advantage. โข Strong ownership, communication, and collaboration skills, with the ability to drive AI initiatives from experimentation through production.