AI Engineer (LLM / GenAI)

Key Responsibilities: Solution Architecture & Deployment: - Design and deploy secure, scalable GenAI architectures integrated into applications - Build and deploy REST APIs for AI/ML models - Work with Docker, Kubernetes in cloud environments (AWS/Azure/GCP) GenAI & LLM Development: - Fine-tune and optimize LLMs (GPT, VAEs, GANs, transformer-based models) - Implement RAG pipelines, embedding, and prompt engineering techniques - Work with commercial and open-source LLMs (GPT, Claude, LLaMA, Phi) Agentic AI Development: - Build and deploy AI agents using LangChain, LangGraph, CrewAI, Autogen, AgentFlow - Implement multi-agent systems, orchestration, tool integration, and state management - Develop autonomous or semi-autonomous workflows for business use cases MLOps & Optimization: - Set up end-to-end MLOps pipelines (CI/CD, monitoring, retraining) - Optimize performance, scalability, and infrastructure costs - Use tools like Git, Docker, Kubernetes, vector databases Application Development & Data Integration: - Develop APIs using FastAPI / Node.js - Work with React, TypeScript, async patterns, WebSockets/SSE - Handle data integration using REST APIs, SQL, and external systems Cross-Functional Collaboration: - Partner with Engineering, Product, and Data teams - Communicate complex AI concepts clearly to technical and non-technical stakeholders - Stay updated with the latest advancements in GenAI and AI agents Required Skills: - Strong proficiency in Python, SQL, and GenAI frameworks (e.g., LangChain) - Hands-on experience with LLMs, RAG, embedding, and prompt tuning - Experience building AI agents and multi-agent systems - Experience with cloud platforms (AWS/Azure/GCP) and containerization - Strong knowledge of REST APIs and data integration - Experience with FastAPI, Node.js, React, TypeScript - Understanding of MLOps and deployment practices - Strong analytical, problem-solving, and communication skills Preferred: - 4+ years of experience with GenAI/LLMs in production - Experience with agent orchestration frameworks (CrewAI, LangGraph, Autogen) - Exposure to client-facing AI solutions or cross-functional projects - Open-source contributions, research, or AI project portfolio Requirements - Strong proficiency in Python, SQL, and GenAI frameworks (e.g., LangChain) - Hands-on experience with LLMs, RAG, embedding, and prompt tuning - Experience building AI agents and multi-agent systems - Experience with cloud platforms (AWS/Azure/GCP) and containerization - Strong knowledge of REST APIs and data integration - Experience with FastAPI, Node.js, React, TypeScript - Understanding of MLOps and deployment practices - Strong analytical, problem-solving, and communication skills Benefits - Competitive salary and performance-based bonuses. - Comprehensive insurance plans. - Collaborative and supportive work environment - Chance to learn and grow with a talented team. - A positive and fun work environment