Role: SRE / OPS -GenAI
Location: Chennai, Kolkata, Hyderabad, bangalore,Pune, Delhi
Exp: 6-10 yrs
Mode of interview : virtual
Must Have Skills:
- Python Dev (KARAT Completion)
- GenAI App Dev ( LangChain, LangGraph, RAG Pipelines)
- GCP/AWS/OpenAI Platform Experience
Core Technical Skills
- Strong programming proficiency in Python (mandatory)
- Experience in SRE / DevOps / Production Support roles
- Good understanding of Linux systems and networking
- 4–10 years in SRE / DevOps / Production Engineering
- Minimum 1+ year supporting GenAI / ML workloads (preferred)
- Bachelor's/Master's in Computer Science or related field
Good to have:
GenAI Capabilities (Mandatory)
- Experience supporting LLM-based applications in production
- Familiarity with:
- Prompt engineering basics
- RAG-based systems
- LLM APIs (OpenAI, Vertex AI, AWS Bedrock)
- Understanding of:
- LLM failure modes (hallucination, latency, rate limits)
Cloud & Platform Experience (Mandatory)
- Hands-on experience with:
- AWS and/or GCP
- Experience with:
- Kubernetes (EKS/GKE preferred)
- Docker
- Familiarity with serverless and microservices architecture
Observability & Automation
- Experience with monitoring tools:
- Prometheus, Grafana, Datadog, ELK stack
- Strong scripting/automation skills
- Incident management and troubleshooting expertise
