Harsh Sanas

About

Full-stack engineer with a strong applied AI bent who has built both a real-time EV charging platform and a production text-to-SQL system. Particularly compelling for teams needing someone who can bridge frontend, backend, infrastructure, and LLM evaluation/safety work, with experience shipping under early-stage ambiguity and integrating software with real-world hardware.

Key Strengths

• End-to-end full-stack ownership of EV charging features
• Built real-time systems integrating web apps with physical chargers
• Strong TypeScript-driven API and frontend contract design
• Production AI feature delivery for text-to-SQL
• Model benchmarking and selection using accuracy, latency, and cost
• Grounded LLM system design with validation and safety checks
• Production monitoring and regression analysis for AI systems
• Improved schema grounding to raise execution accuracy without changing the model
• Thoughtful human-in-the-loop design for high-risk AI workflows
• Able to ship in ambiguous early-stage environments
• Delivered a production-ready EV charging platform in about two months
• Shipped production LLM agents with 99.5%+ uptime and sub-2-second latency
• Delivered measurable business impact: 45% reduction in support handling time
• Generated approximately $1.2M annual support cost savings
• Improved customer satisfaction by 18%
• Strong reliability engineering for LLM systems under API rate limits and latency spikes
• Designed robust fallback and confidence-based escalation to human agents
• Architected auditable multi-step agent workflows with structured outputs and state management
• Built schema-validated, guardrailed integrations that prevented malformed data from breaking downstream systems
• Data-driven evaluation and monitoring across offline tests and live production metrics
• Improved live reliability by reducing fallback rates 30% through prompt and classifier iteration
• Handled messy ERP integrations with normalization, data quality controls, and idempotent writes
• End-to-end ownership of Python backend services for real-time telemetry systems
• Designing robust state-reconciliation and idempotency to handle out-of-order/duplicate OCPP events
• Building and operating Kubernetes deployments with Helm, probes, autoscaling, and zero-downtime rollouts
• Implementing GitOps CI/CD with GitHub Actions + ArgoCD and fast rollback via Git revert
• Planning and executing cloud-to-on-prem migrations using blue-green cutover and CDC with zero downtime
• Designing Kafka streaming pipelines for bursty high-frequency data with ordering and deduplication controls
• Improving ML forecasting reliability via better preprocessing and minimum-history thresholds

Experience

Education

Skills

Languages