Batnitesh.reddy open to SDE-2 roles
root span · agent.run("nitesh")

I build AI agents that are faster, cheaper and more reliable.

Software Engineer at BrowserStack. I work on AI coding agents, LLM observability and evals. My job is reading traces to find out why an agent was slow or wrong. So this page is one too.

Spans · experience

Where the time went

2+ years across backend systems and production AI agents.

span · job.browserstack

BrowserStack

role
Software Engineer
where
Mumbai
start
Sep 2025
status
running
child span · AI evals and LLM observability
  • Designed and built a two-language AI Observability SDK (Node.js/TypeScript and Python) that traces LLM apps with zero code changes, using OpenTelemetry across OpenAI, Anthropic, AWS Bedrock, Google Vertex AI and LangChain.
  • Built a custom telemetry pipeline: smart span filtering, finding the caller from the call stack, trace propagation across services, and decorators (@workflow, @agent, @task, @tool) for structured tracing of agent workflows.
  • Built a scalable LLM evaluation platform with 20+ metrics: faithfulness, answer relevancy, contextual precision/recall, bias detection, safety scoring, RAGAS and G-Eval, with async job processing and concurrent workers.
  • Designed a multi-variant experiments framework: dataset versioning, prompt lifecycle management, batch evaluation, human-review annotation queues, and model comparison across quality, latency and cost.
child span · Test Companion, an AI coding agent for testers
  • Improving the production agent's speed, reliability and cost using telemetry.
  • Removed an optimisation that was adding model calls. One representative workflow went from 15 → 4 model calls, $0.372 → $0.229 per task and 149s → 36s runtime.
  • Tuned prompt-cache use from production telemetry: halved the cache keepalive, saving about $240–300 a month while keeping warm resumes fast. Tested a further cut and rejected it because it hurt resume reliability.
  • Found that 58% of production tasks repeated identical tool calls. Uncovered eight separate looping root causes and built safeguards: parallel-safety gates, tool-call batching and completion validation.
  • Root-caused a task that read the same file 254 times without finishing: the dedup cache keyed on file path only, not path plus line range. Reproduced it at the wire level and fixed the read tracking.
TypeScriptPythonNode.jsOpenTelemetryClickHouseLLM evalsAWS BedrockVertex AI
span · job.credflow

Credflow

role
SDE 1
where
Noida
start
Aug 2024
end
Aug 2025
  • Built LLM agents with LangChain and Vertex AI that read complex GSTR-3B CAM sheets (10–15 sub-sheets) to automate credit underwriting, with Kafka for event-driven processing.
  • Built backend services for the Loan Origination and Loan Management systems.
Node.jsTypeScriptKafkaMongoDBPostgreSQLLangChain
Trace timeline

The whole run, on one screen

Every bar is a real piece of my work. Click a row to jump to its details.

rootjob tool call (side project)log (note)
Jobs are placed by their real dates. Side projects are from the last few weeks and are placed in order, not by exact date.
Tool calls · side projects

Things I've built lately

Each one started as a small, real problem. Scroll to replay the session: the problem, the call, the result.

Logs · today I learned

How things really work

Deep dives into everyday engineering, one topic a day, below the surface.

Next span

Let's add one together.

Open to SDE-2 roles in AI agents, LLM tooling and backend systems.

Your visit, traced live
time you spent on each part00:00
Counted in your browser only. Nothing is sent or stored anywhere.
tracing your visit 00:00 · hero