Gen. AI Engineer
About The Position
Kaleidoscope, an Infosys Company, is seeking a Senior GenAI / Agentic AI Engineer to design, build, and deploy enterprise-scale AI applications leveraging large language models (LLMs), Retrieval-Augmented Generation (RAG), Agentic AI, and cloud-native technologies. This is a hands-on engineering role focused on developing production-ready AI platforms from architecture through deployment. The role calls for experience building scalable AI solutions, integrating LLMs into enterprise applications, and delivering secure, reliable systems for production environments. The technical environment includes Python, JavaScript/TypeScript, SQL, AI and web frameworks, major cloud platforms, vector databases, DevOps tools, and AI platforms. Kaleidoscope is an equal opportunity employer and considers qualified applicants without regard to the protected characteristics listed in the posting.
Requirements
- At least 8 years of software engineering, cloud engineering, AI/ML, or platform engineering experience.
- At least 3 years of hands-on experience building production Generative AI or LLM-based applications.
- Strong expertise with Python and API development using FastAPI, Flask, or similar frameworks.
- Experience building RAG solutions and working with vector databases such as Pinecone, Weaviate, Chroma, Milvus, or Azure AI Search.
- Experience with Agentic AI frameworks including LangChain, LangGraph, CrewAI, LlamaIndex, Semantic Kernel, or AutoGen.
- Strong understanding of prompt engineering, tool calling, agent orchestration, and workflow automation.
- Experience developing cloud-native applications on AWS, Azure, or GCP.
- Hands-on experience with Docker, Kubernetes, Terraform, CI/CD pipelines, and modern DevOps practices.
- Experience integrating enterprise AI applications with databases, APIs, and business systems.
- Strong understanding of security, governance, and responsible AI best practices.
Nice To Haves
- Experience implementing Graph RAG and knowledge graph solutions.
- Experience with MCP (Model Context Protocol) architecture.
- Experience deploying models using vLLM, Hugging Face, Triton, or TensorRT-LLM.
- Experience with Databricks, Spark, Kafka, Snowflake, or modern data engineering platforms.
- Experience building AI applications in regulated industries such as Financial Services, Healthcare, or Insurance.
- Azure, AWS, Google Cloud, or Databricks AI certifications.
Responsibilities
- Design and develop enterprise Generative AI applications using LLMs, RAG, Graph RAG, and multi-agent architectures.
- Build scalable document ingestion, embedding, retrieval, and vector search pipelines.
- Develop AI agents using frameworks such as LangChain, LangGraph, CrewAI, LlamaIndex, AutoGen, or similar technologies.
- Create secure backend services and APIs using Python, FastAPI, Flask, or comparable frameworks.
- Build AI-powered web applications using front-end technologies such as React, Angular, or Next.js.
- Deploy cloud-native AI solutions across AWS, Azure, and GCP using Docker, Kubernetes, and Infrastructure-as-Code.
- Implement observability, monitoring, LLMOps, and governance to support production reliability and responsible AI practices.
- Collaborate with product, engineering, architecture, and business stakeholders to deliver enterprise AI solutions.
Stand Out From the Crowd
Upload your resume and get instant feedback on how well it matches this job.
What This Job Offers
Job Type
Full-time
Career Level
Senior
Education Level
No Education Listed
