Seema Seema

Built Bifrost, an internal observability platform integrating MCP for LLM-based querying across traces, logs, metrics, and service topology, giving engineering teams automated root-cause insight into failing services; used ClickHouse for storage, Quickwit for ingestion, and Grafana for dashboards Designed automated on-call reporting pipeline and agentic Claude AI skills for incident summarization and root-cause suggestion, directly supporting engineering decision-making during incidents; automated alert-to-ticket workflows via n8n and OpsGenie, integrated with Slack, Jira, and Confluence, eliminating 3+ hours of manual work per week Audited region-based infrastructure configurations and coordinated readiness across multiple teams for Disaster Recovery drills, strengthening operational risk controls and audit preparedness

Platform Engineering Intern at Slice (Fintech) (2026-03 – Present)

• Built Bifrost, an internal observability platform integrating MCP for LLM-based querying across traces, logs, metrics, and service topology, giving engineering teams automated root-cause insight into failing services; used ClickHouse for storage, Quickwit for ingestion, and Grafana for dashboards
• Designed automated on-call reporting pipeline and agentic Claude AI skills for incident summarization and root-cause suggestion, directly supporting engineering decision-making during incidents; automated alert-to-ticket workflows via n8n and OpsGenie, integrated with Slack, Jira, and Confluence, eliminating 3+ hours of manual work per week
• Audited region-based infrastructure configurations and coordinated readiness across multiple teams for Disaster Recovery drills, strengthening operational risk controls and audit preparedness
• Built a self-service internal tool for cloning Kubernetes namespaces via web UI with TTL-based auto-expiry, removing a recurring manual provisioning bottleneck for platform engineers

AI & Full Stack Engineer Intern at PhoqTek Labs (2025-07 – 2025-11)

• Built scalable RAG pipeline with FAISS vector search indexing 1,000+ document chunks for low-latency semantic retrieval
• Orchestrated LLM inference pipeline with LangChain across 2 models with automatic failover, improving AI workflow reliability
• Developed real-time data streaming with SSE supporting 50+ concurrent connections; containerized with Docker and Redis caching

Software Engineering Intern at IEEE Hyderabad Section (2024-08 – 2024-10)

• Developed RESTful APIs in Express.js with RBAC, JWT authentication, and optimized MongoDB schemas to reduce query latency

Selected Mentee (Top 15% of 20,000+ Applicants) at Amazon ML Summer School (2024-07 – 2024-08)

• Trained on supervised learning, deep learning, NLP, and computer vision by Amazon scientists; built distributed data pipelines using Apache Spark and MapReduce; presented capstone on scalable recommendation systems

B.E. in Artificial Intelligence and Data Science – Chaitanya Bharathi Institute of Technology (CBIT) (2026-05)