Description :

Job Title: Senior Python Gen AI Engineer

Location: Hyderabad

Employment Type: Full-time

About the Role :

We are looking for an experienced Senior Python Gen AI Engineer with strong expertise in Large Language Models (LLMs), Prompt Engineering, RAG architectures, and agentic AI.

The ideal candidate will have hands-on experience building and deploying AI solutions on AWS, leveraging tools like Bedrock, SageMaker, LangChain, n8n, crewAI, and AutoGen.

You will play a key role in designing high-performance Gen AI systems, fine-tuning models, building intelligent workflows, and deploying scalable AI applications.

Key Responsibilities :

Generative AI Development :

- Develop end-to-end generative AI solutions using AWS services, including Bedrock, SageMaker, Lambda, and ECS/EKS.

- Build and deploy LLM applications using Python libraries such as LangChain, transformers, crewAI, and AutoGen.

- Fine-tune LLMs using AWS SageMaker, LoRA techniques, and HuggingFace transformers.

- Create optimized prompts and prompt chains using LangChain for enhanced output quality and system reliability.

RAG & Search Systems :

- Design and implement robust Retrieval-Augmented Generation (RAG) pipelines using AWS OpenSearch and LangChain.

- Integrate vector stores, embeddings, and retrieval strategies to support scalable search-based Gen AI applications.

Agentic AI & Workflow Automation :

- Build AI agents using crewAI or AutoGen with seamless AWS integration.

- Develop and automate agentic workflows using n8n, including creating custom nodes, handling triggers, and chaining multiple agents.

- Implement production-ready workflows similar to reference architectures (e.g., n8n.io/workflows/6270).

Cloud Deployment & Infrastructure :

- Containerize and deploy Gen AI applications using Docker and orchestrate on AWS ECS/EKS.

- Build serverless compute solutions with AWS Lambda.

- Ensure system reliability, high availability, and performance for production workloads.

Monitoring, Logging & Performance :

- Monitor application performance using Amazon CloudWatch, wandb, and other observability tools.

- Optimize model performance, system latency, and compute cost.

- Troubleshoot system issues and implement continuous improvements.

Must-Have Qualifications :

- 5+ years of hands-on Python development experience, including backend engineering.

- Minimum 2 years of experience working with LLMs and Generative AI technologies.

Strong expertise in :

- AWS Bedrock, SageMaker, Lambda, boto3

- LLM fine-tuning, LoRA, transformers

- LangChain for prompt engineering and orchestration

- AI or AutoGen for building AI agents

Experience with :

- n8n workflows and agentic automation

- Building RAG pipelines and vector-based retrieval

- Deploying applications in containerized environments (Docker, ECS/EKS)

Preferred Qualifications :

- AWS Certifications Machine Learning Specialty or Solutions Architect preferred.

- Familiarity with llama-index, n8n workflow templates, or similar RAG frameworks.

- Experience contributing to open-source Gen AI tools or model fine-tuning initiatives.