About the Role
We are looking for a hands-on GenAI Engineer to design, develop, and deploy enterprise-grade AI applications powered by Large Language Models (LLMs). This role is focused on building AI agents, implementing RAG workflows, and developing scalable GenAI solutions that integrate with enterprise systems.
The ideal candidate has strong Python development skills, practical experience working with LLMs, and hands-on exposure to agent frameworks such as LangGraph, CrewAI, AutoGen, or PydanticAI. You will work closely with AI, platform, and product teams to build production-ready AI solutions that deliver real business impact.
What You'll Be Doing
- Design and develop AI agents using modern agent orchestration frameworks such as LangGraph, CrewAI, AutoGen, or PydanticAI.
- Build and optimize Retrieval-Augmented Generation (RAG) pipelines and LLM-powered workflows.
- Develop reusable components for agent orchestration, task automation, and enterprise AI applications.
- Engineer prompts, workflows, and agent interactions to improve accuracy, reliability, and user experience.
- Deploy and integrate AI solutions using Databricks, Azure ML, and cloud-native services.
- Build APIs and real-time integrations using REST APIs, WebSockets, and event-driven architectures.
- Collaborate with platform and engineering teams to ensure scalable, secure, and production-ready deployments.
- Contribute to CI/CD automation, code quality, testing, and documentation standards.
Required Experience & Skills
- 3–5 years of experience in Machine Learning, Artificial Intelligence, or related software engineering roles.
- At least 1 year of hands-on experience building enterprise Generative AI applications.
- Strong experience with Python and modern software development practices.
- Practical experience working with Large Language Models (GPT, Claude, Llama, or similar).
- Hands-on experience building AI agents using LangGraph, CrewAI, AutoGen, PydanticAI, or similar frameworks.
- Strong understanding of RAG architectures, vector databases, and LLM application development.
- Experience with Databricks and cloud-based deployment environments.
- Knowledge of REST APIs, WebSockets, and event-driven systems.
- Experience with Git, CI/CD pipelines, and agile development methodologies.
Preferred Skills
- Experience with MLOps or LLMOps workflows.
- Exposure to model monitoring, evaluation, and governance.
- Understanding of enterprise security, compliance, and responsible AI practices.
- Experience working with Azure ML or similar AI platforms.
- Familiarity with AI-assisted development tools such as GitHub Copilot, Windsurf, or Codeium.
Ideal Candidate
This role is best suited for engineers who are actively building GenAI applications rather than primarily working in data science, project management, or traditional machine learning roles. We are looking for professionals who have experience taking LLM-powered applications from prototype to production and can confidently build AI agents, RAG pipelines, and enterprise AI solutions.
