Sri Nikitha Veerla

• Automated log parsing and diagnostics with Python/C++; reusable CLI tools.
• SQL jobs and dashboards that improved Argos and DegreeWorks data quality.
• Runbooks and knowledge base articles that reduced escalations.
• Ticket workflow insights that flagged SLA risks and lowered MTTR.
• Monitoring snippets to surface common failure modes quickly.

• Optimized backend APIs integrating ML inference endpoints.
• Containerized model services with safe rollouts and telemetry.
• Validation and rate-limiting patterns for high-traffic routes.
• Reduced p95 latency with schema/index tuning and caching.
• Improved CI stability with tests and static checks.

• Built responsive UI components with predictable state and secure forms.
• Code-splitting and index tuning to improve perceived performance.
• REST endpoints with clear error contracts and sanitization.
• Session/token auth hardening and role-based access patterns.
• Tests and lint rules in CI for stable main branches.

Focus: AI/ML systems, distributed computing, cloud-native development.

EDC core member; projects in anomaly detection, forecasting, and scalable APIs.

Early-warning malware pipeline using syscall and process-tree signals with a lightweight, interpretable design.

• Multi-signal feature engineering across syscalls, process trees, and heuristics.
• Comparative study of SVM, Random Forest, and boosted models.
• Interpretable indicators that support analyst triage.
• Lightweight runtime suitable for constrained devices.

• High precision/recall on curated malware datasets.
• Low memory footprint during profiling.
• Stable detection under mild obfuscation.

Affect-aware recommendation that maps detected mood to track attributes for compact, near real-time inference.

• Dataset augmentation for robust training on compact models.
• Mood to tempo/key/energy mapping for playlist curation.
• User feedback loop to adapt preferences over time.
• Inference path optimized for mobile-class hardware.

• Above-baseline accuracy on test splits.
• Reduced perceived mismatch in A/B tests.
• Low-latency demo performance.

Second Place — NASA Space Apps Hackathon

Built an MVP leveraging NASA datasets and APIs to visualize earth observation data and flag weather anomalies with confidence scores.

• Interactive mapping dashboard with filters and drill-downs.
• Streamlined ingestion pipeline with validation and caching.
• Clear roadmap for scaling compute, storage, and UX.
• Collaborated across roles to deliver demo-ready features in 24 hours.
• Positive judge feedback on clarity, impact, and feasibility.

Entrepreneurship Development Cell (EDC) — JNTU Hyderabad

Promoted innovation and entrepreneurship through student events and mentorship—supporting idea sprints, MVPs, and hackathons.

• Organized startup idea competitions, hackathons, and awareness sessions.
• Collaborated with mentors and industry advisors for guidance.
• Built a supportive environment for startups and innovation activities.

AWS — Honeywell Program