Responsibility
Job Title: GenAI & Agentic AI Engineer
Experience: 5+ Years
Employment Type: Full-Time
Location: Remote / As per business requirement
Role Summary
We are looking for an experienced GenAI & Agentic AI Engineer with strong hands-on expertise in Python, AWS, Generative AI, LLMs, Agentic AI, MCP Servers, RAG pipelines, Vector Databases, EKS, and PyTorch. The ideal candidate will be responsible for designing, developing, deploying, and optimizing production-grade AI/LLM solutions, intelligent AI agents, and scalable RAG-based applications on AWS.
The candidate should have strong experience building LLM-powered applications, multi-agent workflows, MCP-based integrations, retrieval-augmented generation pipelines, model inference, and cloud-native AI solutions.
Key Responsibilities
- Design and develop Generative AI and Agentic AI applications using Python, LLMs, and modern AI frameworks.
- Build and deploy AI agents and multi-agent workflows supporting planning, reasoning, tool usage, and autonomous task execution.
- Develop and integrate MCP (Model Context Protocol) servers to connect LLMs and AI agents with enterprise tools, APIs, databases, and external systems.
- Design and implement scalable RAG pipelines, including document ingestion, chunking, embedding generation, retrieval, reranking, and LLM-based response generation.
- Work with Vector Databases to enable semantic search, knowledge retrieval, and high-performance similarity search.
- Develop and fine-tune AI/ML models using PyTorch and related deep learning frameworks.
- Integrate and optimize LLMs and foundation models for enterprise GenAI use cases, including prompt engineering, evaluation, and inference optimization.
- Develop production-ready Python-based AI services, APIs, and backend components and deploy them on AWS using services such as EKS, compute, storage, networking, and security components.
- Build and manage containerized AI applications using Docker and Kubernetes/Amazon EKS.
- Implement scalable, highly available, and secure architectures for LLM, RAG, and Agentic AI solutions.
- Optimize model performance, latency, scalability, resource utilization, and inference costs while implementing monitoring, logging, evaluation, and observability.
- Collaborate with data scientists, ML engineers, software engineers, architects, and business stakeholders to translate requirements into production-ready AI solutions.
- Follow best practices for AI security, data privacy, responsible AI, prompt security, and enterprise governance.
- Troubleshoot and continuously improve AI pipelines, model performance, retrieval accuracy, and agent reliability.
Required Skills & Experience
- Strong hands-on experience with Python for AI/ML development and production applications.
- Strong expertise in AWS and cloud-native AI/ML deployments.
- Hands-on experience with Generative AI, LLMs, and Agentic AI.
- Strong experience developing and integrating MCP (Model Context Protocol) Servers.
- Hands-on experience designing and implementing RAG pipelines.
- Experience working with Vector Databases for semantic search and knowledge retrieval.
- Strong experience with PyTorch and deep learning frameworks.
- Hands-on experience with Docker, Kubernetes, and Amazon EKS.
- Experience with LLM inference, prompt engineering, model evaluation, and optimization.
- Strong understanding of production-grade AI architecture, security, scalability, and observability.
Mandatory Skills
- Python, AWS, Generative AI, Agentic AI, LLM, MCP Server, RAG Pipelines, Vector Database, Amazon EKS, PyTorch
Key Skills
- Generative AI, Agentic AI, Large Language Models (LLMs), MCP Servers, RAG, Vector Databases, Python, PyTorch, AWS, Amazon EKS, Kubernetes, Docker, AI Agents, Multi-Agent Workflows, Prompt Engineering, LLM Inference, Model Evaluation, AI Observability, Enterprise AI