Machine Learning Engineer – Conversational AI & Personalization

₹30,00,000 - ₹40,00,000 a year

Role Overview

We are seeking a highly skilled Machine Learning Engineer to build and scale AI-powered conversational and personalization systems. This role focuses on designing robust ML architectures that integrate large language models (LLMs), retrieval systems, and recommendation engines into reliable, production-grade platforms.

You will work at the forefront of applied AI—developing multilingual NLP systems, optimizing LLM orchestration, and deploying scalable machine learning pipelines that power intelligent chat, contextual recommendations, and personalized user experiences.

The ideal candidate thrives in fast-paced environments, understands both modern LLM ecosystems and classical ML approaches, and has a strong foundation in production ML system design.

Key Responsibilities

Conversational AI & LLM Engineering

Design and deploy scalable conversational AI systems supporting multi-turn dialogue, contextual memory, and personalization.Build and optimize LLM orchestration layers including prompt engineering, routing logic, fallback strategies, and multi-model selection.Integrate and manage models across platforms such as OpenAI, Claude, Qwen, LLaMA, and other modern LLM providers.Develop evaluation pipelines to measure response accuracy, contextual alignment, tone consistency, and hallucination reduction.Optimize production systems for latency, throughput, and cost efficiency using batching, caching, and prompt optimization techniques.

Retrieval & Knowledge Augmentation

Implement and manage vector search infrastructure using tools such as Qdrant, Pinecone, FAISS, or equivalent.Architect Retrieval-Augmented Generation (RAG) pipelines to enhance model outputs with contextual knowledge.Work with structured and unstructured datasets to improve relevance and factual accuracy.Design document ingestion, embedding, and indexing workflows for scalable knowledge systems.

Personalization & ML Pipelines

Build end-to-end ML pipelines for user segmentation, classification, and recommendation systems.Develop ranking models and intelligent content transformation systems combining LLMs with traditional ML techniques.Create adaptive personalization engines that evolve based on user behavior and contextual signals.Ensure robust monitoring, retraining strategies, and model lifecycle management.

Multilingual NLP & Model Optimization

Fine-tune and deploy models for Hindi and multilingual Natural Language Understanding (NLU) and Natural Language Generation (NLG).Experiment with and productionize open-source LLMs such as Qwen, Mixtral, and LLaMA in low-latency environments.Evaluate and optimize closed-source LLM performance for cost and quality trade-offs.Implement pipelines using frameworks like LangChain, RAG toolkits, FAISS/Chroma vector stores, and multilingual translation systems such as IndicTrans2 and NLLB.

Cross-Functional Collaboration

Partner with product teams and domain experts to translate business needs into scalable ML solutions.Contribute to system design decisions around architecture, scalability, and deployment.Continuously benchmark, experiment, and iterate to improve model performance and system robustness.Drive best practices in ML experimentation, evaluation, and production deployment.

Required Qualifications

5+ years of experience in Machine Learning or Applied AI roles.Strong hands-on expertise with Large Language Models, RAG systems, and vector databases.Proven experience building and deploying production-grade ML systems.Proficiency in Python and ML/NLP frameworks such as PyTorch, TensorFlow, and Hugging Face Transformers.Experience with multilingual NLP systems, particularly Indian language processing.Deep understanding of prompt engineering, evaluation methodologies, and hallucination mitigation.Solid knowledge of scalable system design, model serving, latency optimization, and cost-aware deployment strategies.

Core Skills

Machine Learning Engineering · Generative AI · Large Language Models (LLMs) · Retrieval-Augmented Generation (RAG) · Vector Search Systems · Multilingual NLP · Model Fine-Tuning · Recommendation Systems · Production ML Architecture · Scalable AI Systems