Machine Learning Engineer – AI Platform Reliability (LLM Inference, RAG)
Cisco · Hyderabad
| Company | Cisco |
|---|---|
| Role | Machine Learning Engineer – AI Platform Reliability (LLM Inference, RAG) |
| Location | Hyderabad |
| Work mode | Hybrid |
| Experience | 3–6 years |
| Job type | Full-time |
About this job
Cisco is hiring a Machine Learning Engineer in Hyderabad for the Splunk AI Platform and Services team. The team runs multi-tenant LLM inference, vector DB and RAG, MCP and AI developer services across hybrid clouds.
The role sits between SRE, distributed systems and ML infrastructure: you will keep these AI services available and cost-efficient, tune GPU inference, automate rollouts and self-healing, and lead incident response. The role is hybrid.
Eligibility
- Bachelor's with 5+ years, or master's with 3+ years, of relevant experience
- 3+ years of Python, Go or Java for tooling or backend services
- Running containerised systems on Kubernetes with CI/CD
- Monitoring with Prometheus, Grafana, Splunk or OpenTelemetry
- vLLM, TensorRT-LLM, Ray Serve or GPU scheduling is a plus
Skills required
What you will do
- Run and tune LLM inference, RAG and MCP services
- Set SLOs, health checks and dashboards
- Automate rollouts, autoscaling and recovery
- Tune GPU throughput, batching and caching
- Lead incidents and root cause analysis
How to apply
- Open the official Cisco job page with the Apply button and submit your application there.
- Tailor your resume to AI or ML services you kept reliable in production, and GPU or latency gains you made.
Before the interview, prepare:
- vLLM basics: batching, KV cache and throughput
- SLOs for an inference API
- Canary rollouts and automatic rollback
- Running a vector database in production
Get jobs like this every day on WhatsApp. Free, no spam, only verified openings.
Join channelStay safe: DailyITJobs is not a recruitment agency and is not connected to Cisco. Apply only on the official website. Never pay anyone for a job, interview or offer letter.