Lead Gen AI Engineer

About the Role:

We are looking for a Software Engineer who combines deep data engineering expertise with hands-on experience in Generative AI and Agentic AI system development on AWS Cloud.

This role is ideal for someone who can design, build, and deploy production-grade GenAI workflows integrating LLMs, vector databases, and orchestration frameworks—with the same rigor as a traditional data system.

Key Responsibilities:

• Design and maintain data pipelines and AI data infrastructure on AWS (Glue, Lambda, S3, Redshift, Step Functions, Athena, etc.).
• Develop and deploy LLM-based applications and Agentic AI workflows using frameworks like LangChain, LlamaIndex, or AutoGen.
• Build RAG (Retrieval-Augmented Generation) pipelines using AWS services (S3 + Bedrock + SageMaker + OpenSearch/Vector DB).
• Implement agentic reasoning, tool calling, and orchestration for multi-agent workflows.
• Containerize and deploy AI services using Docker, ECS, or EKS, ensuring scalability, cost-efficiency, and observability.
• Integrate AWS Bedrock, SageMaker, or OpenAI APIs with internal data systems and applications.
• Set up monitoring, tracing, and model observability using AWS CloudWatch, X-Ray, or third-party LLMOps tools.
• Collaborate with ML engineers, data scientists, and architects to take GenAI prototypes to production-ready deployments.

Required Skills & Experience:

• 6–10 years of total experience in Data Engineering with strong AWS background.
• Proficiency in Pyspark with hands-on production grade experience.
• Hands-on experience with GenAI solutions in real-world environments (not just demos or PoCs).
• Working knowledge of Agentic AI frameworks (LangChain, LlamaIndex, AutoGen, or similar).
• Good hands-on experience in Python
• Cloud experience is must have, AWS is preferred.
• Experience with RAG architecture, vector databases (OpenSearch, Pinecone, FAISS, Chroma, or Milvus), and embedding models.
• Understanding of LLMOps, prompt lifecycle management, and performance monitoring.
• Practical experience deploying workloads on AWS ECS/EKS, setting up CI/CD pipelines, and managing runtime performance.
• Familiarity with IAM, VPC, Secrets Manager, and security best practices in cloud environments.

Nice to Have:

• Experience with AWS Bedrock for model hosting or SageMaker for fine-tuning and evaluation.
• Exposure to multi-agent architectures and autonomous task orchestration.
• Contributions to open-source GenAI projects or internal AI platform initiatives.

For Quick Response- Interested Candidates can directly share their resume along with the details like Notice Period, Current CTC and Expected CTC at anubhav.pathania@impetus.com