Responsibilities: 

- Partner with product, ML, and DevOps teams to translate business goals into GenAI software solutions. 

- Design, build, and maintain Python-based GenAI services, APIs, and micro-services—leveraging FastAPI for REST endpoints as well as WebSockets and WebRTC for real-time, bi-directional communication. 

- Implement event-driven architectures (e.g., Kafka, Pub/Sub) for low-latency data ingestion and inference. 

- Containerize and orchestrate services with Docker and Kubernetes for reliable, scalable deployments. 

- Engineer data-lake integrations that handle high-volume structured and unstructured data for RAG and fine-tuning workflows. 

- Enforce modular, reusable, and secure code practices (authN, authZ, secrets management, OWASP). 

- Collaborate closely with data scientists on model packaging, versioning, and inference endpoints. 

- Automate testing and CI/CD pipelines (GitHub Actions, Azure DevOps, or AWS CodePipeline) to ensure rapid, reliable releases. 

- Author and maintain technical documentation, architecture diagrams, and runbooks. 

- Track emerging GenAI and Python ecosystem advances; champion best practices and continuous improvement. 

Requirements: 

- Python Expertise: 4+ years of building production systems with deep knowledge of OOP, type hints, asyncio/concurrency, and performance tuning. 

- Web & API Development: Extensive FastAPI (or Flask) experience creating scalable REST/JSON endpoints around LLM services. 

- System Architecture: Demonstrated ability to design decoupled, event-driven, cloud-native systems that scale horizontally and remain maintainable. 

- Cloud & Containers: Hands-on with Docker and Kubernetes, deploying workloads to Azure AKS, AWS EKS, or GKE. 

- Version Control & CI/CD: Advanced Git workflows plus automated testing, build, and release pipelines (GitHub Actions, Azure DevOps, or AWS CodePipeline). 

- Security & Compliance: Familiarity with OAuth 2.0/JWT, secrets management, and relevant data privacy regulations. 

Preferred Skills: 

- Gen AI Frameworks:  Experience with LLM frameworks or tools for interacting with LLMs such as LangChain, LangGraph, AutoGen and CrewAI 

- Data Pipelines: Experience in setting up data pipelines for model training and real-time inference. 

Professional and Educational Background: 

-  BE / B.Tech / MCA / M.Sc / M.E / M.Tech