Senior AI Engineer

Role : Senior AI Engineer/ AI Developer (full stack)

Experience : 7+ years of experience

About Us

KR Elixir Technology Inc. is a next-generation IT Services company headquartered in Alpharetta, Georgia, USA, specializing in Data, AI, Digital, and Cloud Solutions. While KR Elixir is primarily a services-led organization, we are also investing in and building innovative AI products, enterprise platforms, accelerators, and cloud-native solutions that help organizations modernize application development, API management, enterprise integration, and AI adoption.

Our expertise spans Data Governance, Analytics, Artificial Intelligence, Generative AI, Cloud Engineering, Enterprise Integration, API Platforms, and Digital Product Development for web, mobile, and cloud-native applications. With over 1,000 employees globally, KR Elixir serves clients across the USA, India, UK, Brazil, UAE, Chile, and ANZ.

We are proud recipients of the Fast 100 Asian American Business Award (2020), recognized for innovation and excellence in IT Services. For more information, please visit https://krelixir.com.

We are building a next-generation AI-native platform that unifies API Lifecycle Management, Agentic AI, AI Gateways, Model Context Protocol (MCP), AI Agents, and Enterprise Integration into a single developer experience. Our mission is to help enterprises design, build, secure, test, govern, and deploy APIs and AI agents faster and more intelligently.

As an early-stage startup, we move quickly, value ownership, and encourage innovation. If you're excited about shaping products from the ground up and working directly with customers, we'd love to hear from you.

Role Overview:

As a Senior AI Engineer, you will design, develop, and deploy enterprise AI applications leveraging Large Language Models (LLMs), Agentic AI, Retrieval-Augmented Generation (RAG), and cloud-native technologies.

This is a highly hands-on engineering role requiring strong software development expertise combined with practical experience building AI-powered products, AI copilots, enterprise chatbots, autonomous AI agents, and intelligent automation solutions.

You will collaborate closely with solution architects, product teams, and customers to deliver secure, scalable, and production-ready AI applications.

Key Responsibilities:

AI Solution Development

• Design, develop, and deploy enterprise AI applications using Large Language Models (LLMs).
• Build AI-powered copilots, AI assistants, enterprise chatbots, and intelligent automation solutions.
• Develop autonomous AI agents using Agentic AI frameworks.
• Design and implement Retrieval-Augmented Generation (RAG) pipelines integrating enterprise knowledge sources.
• Build reusable AI services, APIs, and microservices for enterprise applications.

AI Engineering & Development

• Develop backend services using Python and preferably Java.
• Build RESTful APIs and scalable microservices using FastAPI or Spring Boot.
• Integrate enterprise applications with OpenAI, Azure OpenAI, Gemini, Claude, Anthropic, or open-source LLMs.
• Optimize prompts, context management, and AI workflows for enterprise use cases.
• Work with vector databases, embeddings, and semantic search technologies.

AI Frameworks & Orchestration

• Build AI orchestration workflows using LangChain, LangGraph, CrewAI, Google ADK, Semantic Kernel, AutoGen, or similar frameworks.
• Develop multi-agent AI systems with tool calling, function calling, and workflow orchestration.
• Implement Model Context Protocol (MCP) integrations where applicable.
• Design scalable AI pipelines supporting enterprise workloads.

Cloud & Deployment

• Deploy AI applications on AWS, Microsoft Azure, or Google Cloud Platform.
• Containerize applications using Docker and orchestrate deployments using Kubernetes.
• Build CI/CD pipelines for AI application deployment.
• Monitor AI applications for scalability, performance, and reliability.

AI Quality, Security & Governance

• Implement AI evaluation frameworks to monitor model quality and response accuracy.
• Apply guardrails for hallucination mitigation, prompt injection protection, and content moderation.
• Implement PII masking, secure prompt handling, authentication, authorization, and enterprise security best practices.
• Ensure responsible AI and governance standards are followed throughout development.

Collaboration & Innovation

• Collaborate with architects, product managers, data engineers, and business stakeholders.
• Participate in technical design discussions and code reviews.
• Mentor junior engineers and contribute to engineering best practices.
• Continuously evaluate emerging AI technologies and recommend innovative solutions.

Required Qualifications

• Bachelor's or Master's degree in Computer Science, Artificial Intelligence, Engineering, or a related field.
• 7–10 years of software engineering experience.
• 2–3+ years of hands-on experience in Generative AI, LLM application development, or Agentic AI.
• Strong programming skills in Python (Java is an added advantage).
• Experience building production-grade AI applications.
• Hands-on experience with Retrieval-Augmented Generation (RAG).
• Experience working with vector databases and embedding models.
• Strong understanding of prompt engineering and AI evaluation techniques.
• Experience building REST APIs using FastAPI or Spring Boot.
• Experience with Docker, Kubernetes, and CI/CD.
• Experience deploying applications on AWS, Azure, or GCP.
• Excellent problem-solving and communication skills.

Preferred Qualifications

• Experience developing AI copilots or enterprise AI assistants.
• Hands-on experience with LangChain, LangGraph, CrewAI, Google ADK, AutoGen, Semantic Kernel, or similar AI frameworks.
• Experience with Model Context Protocol (MCP).
• Familiarity with MLOps, ModelOps, and AI observability.
• Cloud certifications (AWS, Azure, or GCP) are a plus.
• AI/Generative AI certifications are an added advantage.