Walk-in || Gen AI Engineer

Job Description:

Key Responsibilities & Requirements:

• 3-8 years of software development experience with hands-on expertise in Generative AI, Agentic AI, Machine Learning, or AI-powered application development.
• Strong understanding of Large Language Models (LLMs), Prompt Engineering, Retrieval-Augmented Generation (RAG), AI Agents, Multi-Agent Systems, and Conversational AI solutions.
• Proficiency in Python and experience with frameworks such as LangChain, LangGraph, LlamaIndex, Semantic Kernel, CrewAI, AutoGen, or similar Agentic AI frameworks.
• Hands-on experience with Amazon Bedrock, OpenAI/Azure OpenAI services, embeddings, vector databases, and LLM orchestration platforms.
• Experience designing and developing Agentic AI solutions, including autonomous workflows, tool calling, task planning, memory management, and multi-agent collaboration.
• Strong knowledge of AWS services, including Amazon Bedrock, Lambda, S3, API Gateway, ECS/EKS, DynamoDB, CloudWatch, IAM, and Step Functions.
• Experience building and deploying scalable, secure, and production-grade GenAI and Agentic AI applications on AWS.
• Familiarity with vector databases such as Pinecone, FAISS, Chroma, OpenSearch, or similar technologies.
• Strong understanding of REST APIs, Microservices, CI/CD pipelines, Git, Docker, and cloud-native development practices.
• Ability to work closely with business stakeholders and cross-functional teams to identify use cases and deliver AI-driven solutions.
• Excellent analytical, problem-solving, and communication skills with a passion for innovation and emerging AI technologies.

Preferred Skills:

• Experience implementing enterprise-scale RAG pipelines, AI Agents, Multi-Agent architectures, and workflow automation solutions.
• Exposure to LLMOps, model evaluation, prompt optimization, monitoring, governance, and Responsible AI practices.
• AWS Certifications (Developer Associate, Solutions Architect, AI Practitioner) are a plus.