Role : GenAI Adoption - Platform
Experience : 6 to 10 years
Location : Chennai, Kolkata, Hyderabad, bangalore,Pune, Delhi
Skill set : Platform Engineer with strong Python and Generative AI expertise to design, build, and scale AI-first platforms and infrastructure
Role descriptions / Expectations from the Role
This role focuses on enabling GenAI application development at scale, building reusable frameworks, and integrating LLM capabilities across enterprise systems using AWS/GCP/OpenAI ecosystems.
GenAI Platform Engineering (Core Focus)
- Design and build scalable GenAI platforms and frameworks for enterprise use
- Develop reusable components for:
- Prompt orchestration
- RAG pipelines
- LLM integrations
- Enable internal teams to rapidly build GenAI applications
- Standardize GenAI usage across the organization (templates, SDKs, APIs)
GenAI Application Enablement
- Support development of AI-powered applications such as:
- Chatbots and copilots
- Document intelligence platforms
- AI-driven workflow automation
- Integrate with:
- OpenAI / Azure OpenAI / Google Vertex AI
- Implement:
- Prompt engineering frameworks
- LLM guardrails and evaluation layers
Python Development (Core Skill)
- Build backend services, libraries, and APIs using Python
- Develop platform tooling using:
- FastAPI / Flask
- Create SDKs/microservices for GenAI feature reuse
- Optimize system performance, scalability, and reliability
Cloud Platform Engineering (AWS/GCP)
- Architect and deploy platform services on:
- AWS: Bedrock, Lambda, S3, SageMaker, EKS
- GCP: Vertex AI, Cloud Run, BigQuery, GKE
- Design multi-tenant, scalable AI platforms
- Manage infrastructure as code (IaC) with Terraform or similar tools
- Monitor usage, cost, and performance of GenAI workloads
Data & AI Engineering
- Build and maintain RAG pipelines with vector databases:
- Pinecone, FAISS, Chroma, Weaviate
- Manage embeddings, indexing, and retrieval systems
- Handle structured and unstructured data pipelines
- Ensure data security and governance in AI workflows
DevOps, MLOps & LLMOps
- Build CI/CD pipelines for platform services and AI models
- Implement LLMOps practices:
- Prompt versioning
- Model lifecycle management
- Evaluation pipelines
- Set up observability:
- Logging, tracing, monitoring for AI systems
- Ensure system reliability, scaling, and failover strategies
