.png){kind=logo}
Shashank Sathola
Mid-level Python Backend Developer specializing in cloud-native microservices and AI/ML platforms
Connect with Shashank
Shashank already has a relationship with Reval, so a warm intro from us gets a much better response than cold outreach.
Recommended
Already have an account?
About
Backend/AI engineer who built a production GPU-backed real-time inference API at Nvidia and debugged burst-induced tail latency, cutting P95 by ~29% through dynamic batching and backpressure. Also shipped an end-to-end RAG + agentic operational diagnostics assistant with strict tool controls, evidence citation, confidence gating, and strong production guardrails, plus demonstrated hands-on Postgres optimization (900ms to 40–60ms).
Experience
Education
Key Strengths
- Built and operated high-throughput GPU-backed real-time inference API on Kubernetes across AWS/GCP
- Deep performance debugging of tail latency (P95/P99) using detailed tracing and pipeline breakdown
- Reduced P95 latency ~29% via dynamic batching, backpressure, async handling, and warm GPU pools
- End-to-end ownership of RAG-based LLM assistant (use cases, architecture, ingestion/embeddings, retrieval, backend, confidence/fallbacks)
- Designed reliable agentic workflow with strict plan/execution separation, schema validation, deterministic tool execution, and verification with citations
- Strong production engineering practices in Python: layered architecture, DI, typing/Pydantic, dependency hygiene, structured logging, on-call readiness
- Database performance optimization: composite indexing, query narrowing, and splitting large JSONB payloads; improved query latency ~900ms to 40–60ms
Discover more candidates like Shashank
Search across thousands of pre-screened, high-quality, high-intent candidates on Reval.
Search Talent