ResponsibilitiesGenerative AI & LLM Engineering

• Design, develop, and fine-tune Generative AI solutions using leading LLMs such as GPT-4o, Claude (Anthropic), Gemini, and open-source models (LLaMA, Mistral, etc.)

• Build and maintain End-to-End AI Chatbot systems — from prompt engineering and LLM integration to deployment and monitoring

• Develop production-grade RAG (Retrieval-Augmented Generation) Chatbot pipelines integrating vector search, document chunking, embedding models, and LLM inference

• Implement and manage Vector Storage solutions using FAISS, Qdrant, Weaviate, Pinecone, or similar technologies for semantic search and knowledge retrieval

• Design and deploy Agentic AI systems using frameworks such as LangGraph, AutoGen, CrewAI, or custom multi-agent orchestration workflows

• Integrate AI capabilities with enterprise APIs, databases, and internal platforms via LangChain, LlamaIndex, or equivalent tooling

• Stay current with rapidly evolving AI/ML tools including Hugging Face, Ollama, vLLM, OpenAI APIs, Vertex AI, AWS Bedrock, and Azure OpenAI Service

AI Product Development & MLOps

• Own the end-to-end AI product lifecycle: requirements gathering, model selection, development, testing, deployment, and continuous improvement

• Build and manage scalable AI inference pipelines with performance monitoring, logging, and cost optimization

• Design prompt engineering strategies, evaluation frameworks, and guardrails for safe and reliable LLM outputs

• Implement CI/CD workflows for AI models using MLflow, DVC, or similar MLOps tools

• Collaborate with Data Science and Engineering teams to productionize machine learning and AI models

• Identify opportunities to embed AI capabilities into business workflows, automation, and decision-making processes

Data Engineering & Platform (Foundational Awareness)

• Understand the fundamentals of data pipeline concepts (ETL/ELT, batch and streaming) to effectively collaborate with Data Engineering teams

• Able to read, query, and work with data from common platforms such as Databricks, Snowflake, BigQuery, or PostgreSQL

• Understand data flow from source systems to data warehouses/lakehouses to inform AI model inputs and outputs

• Familiar with vector database concepts and embedding pipelines sufficient to configure and use them in AI projects

• Capable of communicating data requirements clearly to Data Engineers when building AI features or knowledge bases

Collaboration & Innovation

• Partner with product managers, business stakeholders, and engineers to translate business requirements into AI solutions

• Contribute to and promote best practices for AI development, testing, documentation, and responsible AI usage

• Mentor junior engineers and share knowledge on emerging AI tools, frameworks, and research

• Evaluate and adopt new AI/ML technologies and frameworks to keep the team at the forefront of innovation

• Effectively manage multiple priorities and deliver high-quality solutions independently and as part of a team

Qualifications

• Bachelor's degree or higher in Computer Science, Computer Engineering, Information Technology, Artificial Intelligence, or a related field

• 3+ years of hands-on experience in AI/ML engineering with a focus on Generative AI and NLP applications

• Proven experience building Generative AI solutions using GPT-4o, Claude (Anthropic), Gemini, or equivalent LLMs — this is a must

• Hands-on experience with RAG Chatbot development: embedding pipelines, chunking strategies, retrieval tuning, and LLM response generation

• Proficiency in Vector Storage technologies such as FAISS, Qdrant, Weaviate, Pinecone, or ChromaDB

• Experience building End-to-End Chatbot systems including intent handling, context management, multi-turn dialogue, and API integration

• Practical knowledge of Agentic AI frameworks (LangGraph, AutoGen, CrewAI, or similar) for building multi-step, tool-using AI agents

• Strong Python programming skills — Python (required), SQL, JavaScript/TypeScript (a plus)

• Familiarity with popular AI/ML tools and platforms: LangChain, LlamaIndex, Hugging Face, Ollama, vLLM, OpenAI SDK, Vertex AI, AWS Bedrock, or Azure OpenAI

• Experience with prompt engineering techniques including few-shot prompting, chain-of-thought, structured output, and function calling

• Ability to evaluate LLM outputs using metrics and frameworks (RAGAS, TruLens, or custom eval pipelines)

• AI Frameworks: LangChain, LlamaIndex, LangGraph, AutoGen, CrewAI, Hugging Face Transformers

• LLM Platforms: OpenAI (GPT-4o), Anthropic Claude, Google Gemini, Meta LLaMA, Mistral

• Vector Databases: FAISS, Qdrant, Weaviate, Pinecone, ChromaDB

• Cloud & Data: AWS / GCP / Azure AI services, Databricks, Snowflake, PostgreSQL

• MLOps: MLflow, DVC, Docker, Kubernetes (a plus)

• Big Data: Apache Spark, Kafka (a plus)

• Experience in Retail or E-Commerce AI applications (e.g., recommendation engines, pricing AI, conversational commerce)

• Familiarity with fine-tuning and PEFT techniques (LoRA, QLoRA) for LLMs

• Knowledge in machine/statistical learning, computer vision, or time series forecasting

• Experience with AI safety, hallucination mitigation, and responsible AI practices

• Contributions to open-source AI projects or published AI research