Years in Engineering
12+
Building software, automation, and platform systems
bharad@portfolio:~
$whoami
Bharadwaj Pendyala
> Lead Member of Technical Staff
Senior software engineer at Salesforce focused on enterprise communication systems, AI-enabled workflows, and pragmatic architecture that helps teams ship reliably.
Snapshot
- Experience: 12+ years
- Current role: LMTS at Salesforce
- Focus: Platform systems and AI workflows
- Primary stack: TypeScript, Python, AWS serverless
$ls ~/social
Featured work
Writing and talks on building practical, reliable AI systems.
August 10, 202614 min read
Latest writing
Build the Eval Pyramid: A Starter Harness for LLM and Agent Testing
Turn the eval pyramid into a working TypeScript harness with deterministic graders, isolated repeated trials, calibrated model judges, human review, and release gates.
Read articleAug 22, 2026ACM Dallas
Featured talk
Harness Engineering: How Reliable AI Agents Actually Get Built
The model is the engine; the harness is the car. Why most agent pilots stall on reliability rather than capability, and the engineering that closes the gap: tools and permissions, verification loops, guardrails, evals, and human handoff.
Open deckResults at a glance
Selected highlights from professional engineering work.
Years at Salesforce
5+
Growing into lead-level engineering ownership
Current Scope
Org-wide
Workflow platforms, delivery enablement, and AI adoption
Public Builds
3
Portfolio, Jarvis, and a document-aware RAG system
How I work
The principles behind the work featured above.
What I build
- •Enterprise workflow and communication systems that support high-trust delivery.
- •AI-enabled internal tools that reduce manual coordination and improve usability.
- •Platform migrations that improve reliability, observability, and operational clarity.
- •Reusable engineering patterns that help teams ship faster without losing quality.
How I deliver
- •Take ownership of ambiguous platform problems and turn them into shippable systems.
- •Bridge product, engineering, and stakeholder needs with practical technical decisions.
- •Lead rollout readiness through testing, incident response, documentation, and support.
- •Apply AI tooling in ways that improve real engineering velocity instead of adding noise.