Ritesh Srivastava
AI Product Engineer | Applied AI & Platform Delivery
Summary
AI Product Engineer with 7+ years building applied AI and platform tools that turn complex evaluation and operational workflows into reliable, self-service products. At Adobe, lead PRISM and LLMJury, combining LLM evaluation, workflow automation, and production guardrails to reduce Generative AI evaluation cycles by 75–90%. Bring end-to-end delivery experience across requirements discovery, Python engineering, data workflows, enterprise stakeholder collaboration, and measurable product adoption.
Core Skills
Applied AIGenerative AILLM evaluationLLM-as-a-judgeAgent & skill designPrompt engineering
PythonDjangoREST APIsSQLPySparkCLI tool designWorkflow automation
Product deliveryRequirements discoveryStakeholder managementCross-team enablementTechnical documentation
PrefectWeights & BiasesDockerAWSGit
Experience
Adobe Systems — Document Cloud & Artificial IntelligenceNoida, India
Lead Software EngineerJul 2025 – Present
- Lead PRISM, an agentic release-certification platform that converts evaluation runs into auditable go/no-go decisions across 13 locales and 2 pipelines.
- Automated per-locale evaluation reporting, replacing person-weeks of manual Excel scoring and reducing cycle time 75–90% (1–2 days to 3–4 hours).
- Shipped a six-agent skill layer for Claude and Cursor so non-engineering stakeholders can run and interpret evaluations independently.
- Implemented LLM-based triage and publish-isolation guardrails, halving confirmed regression-review volume while protecting shared W&B projects from cross-team data corruption.
- Designed an extensible onboarding model: each new GenAI feature reuses the core engine and agent layer with one parser and one configuration file.
Senior Software EngineerApr 2022 – Jul 2025
- Led LLMJury, a multi-model evaluation framework for Generative AI summary, podcast, and assistant features, removing 100+ manual hours per evaluation cycle.
- Partnered with feature teams to turn ad hoc evaluation requests into self-service tooling adopted across the organization.
- Built a Voxel51 and Labelbox analysis tool that cut manual evaluation effort 80%.
Tata Consultancy ServicesNoida, India
System Engineer — Walgreens, Corteva/DuPont, EatonNov 2018 – Apr 2022
- Embedded with enterprise clients, gathering stakeholder requirements and delivering production CRUD systems, Django automation tools, and REST APIs.
- Built Python data-processing and automation workflows, including EDA workflows and PySpark batch jobs.
Selected Projects
- PRISM — agentic release-certification platform; evaluation scoring, LLM triage, HTML reporting, Prefect and W&B orchestration, and publish-isolation guardrails.
- LLMJury — multi-model Generative AI evaluation framework; 30× faster and 15% more precise than human review.
- Voxel51 & Labelbox tooling — dataset analysis and annotation workflow that reduced manual evaluation effort 80%.
Education
B.Tech, Computer Science & Engineering — FGIET, AKTU, Uttar Pradesh2014 – 2018
Certifications
Certified MLOps Practitioner — Adobe Cohort 01, School of DevOps
Python & Django Full Stack Web Developer — Udemy