Seattle, WAOpen to AI roles

Rithesh Bejjarapu

Staff AI Engineer

Data→Inference→Agents→Production

Staff AI Engineer with 10+ years of experience across software engineering, data platforms, and production AI systems, including years embedded with client and business teams as a consultant. Specializes in local and open-source LLM inference, RAG, agentic systems, and enterprise knowledge platforms, translating ambiguous business problems into shipped AI that delivers measurable impact through decision intelligence, automation, and cost optimization.

$2.1M
revenue at risk surfaced
AI data analyst, Slide
44%
faster security assessments
AI + human-in-the-loop, 9 to 5 days
50%
external AI spend cut
hybrid local inference
10+
years shipping for clients
AI, data, and delivery
01

A T-shaped engineer

Broad foundation across the top, from client delivery and stakeholder alignment to systems engineering. Deep AI-engineering specialization down the stem. Hover or tap any node to see how it fits.

Breadth
Depth / AI Engineering
Depth

Local Inference

Serving quantized open-source models on-prem, routed by task complexity, privacy, latency, and cost.

50%
external AI spend cut
Where
Slide
vLLMllama.cppQuantized Models
02

Experience

10+ years across production AI, data platforms, and enterprise software, with the most recent work centered on end-to-end AI systems.

Slide

Staff Engineer, AI

Nov 2025 to PresentRemote
AI AgentsMCPBigQuerydbtClickHousevLLMLangfuseModel Routing

Customer-Facing AI Agents

  • Interviewed 20+ MSP partners, then shipped AI agents to all partners for backup-failure diagnosis, automated remediation in ConnectWise and PSA/RMM tools, and cyber-insurance guidance; cut related support tickets ~25% and time-to-resolution ~40%.
  • Built root cause analysis agents for a 12-engineer Support team that correlate backup logs, device, and ticket data to propose fixes, cutting triage time ~50%.

Internal AI Platform & Company Brain

  • Built a self-serve AI platform (TypeScript, React, FastAPI) where ~80 employees built 40+ dashboards and 10+ AI apps, such as sales call prep and a PR review bot, cutting time-to-tool from ~1 week to ~1 hour.
  • Designed the company brain and agent layer: 15 RBAC-gated MCP tools across the warehouse, knowledge base, and operational systems, with golden-set evals, Langfuse tracing, and AI security testing before release.

Data, Inference & Decision Intelligence

  • Partnered with Finance and executives to architect the data foundation and semantic layer (BigQuery, dbt, ClickHouse): ~150 tested models from ~12 sources, the single source of truth for reporting and AI agents.
  • Built an AI data analyst agent (LangGraph, Claude) that investigates revenue anomalies and partner signals; surfaced $2.1M in revenue at risk and flagged opportunities tied to 75% of successful upsells.
  • Designed hybrid inference routing between self-hosted open-source models (Qwen on vLLM and Ollama, NVIDIA RTX 5090) and Claude by complexity, privacy, latency, and cost; moved 60%+ of eligible workloads to local inference and cut external AI spend 50%.

Amazon

SDE II, AI & Security Automation

Sep 2022 to Oct 2025New York, NY
LLM SystemsAWS BedrockRAGOpenSearchRisk IntelligenceOrchestration

AI-Assisted Security Assessment

  • Partnered with security assessors to build an LLM assessment system (AWS Bedrock, RAG on OpenSearch) that grounds first-pass reviews in runbooks, security policy, and vulnerability intelligence; cut closure time from 9 days to 5 across ~1,000 assessments a year.
  • Built an AI customer intelligence system that aggregates OSINT, fraud, vulnerability, and internal risk signals; evaluated 300+ companies and surfaced 45 previously unidentified risk signals for investigation.

Assessment Platform & Automation

  • Designed a self-service assessment platform on AWS (Lambda, API Gateway, Java, Python) integrated with ~8 internal security systems, cutting manual setup per assessment ~60% for ~40 assessors.
  • Led design reviews for the team's LLM systems, mentored 2 engineers, and wrote the human-review guidelines for AI-assisted assessments.

JPMorgan Chase & Co.

Senior Software Engineer

Nov 2021 to Sep 2022Wilmington, DE
Low-Code PlatformWorkflow AutomationEnterprise APIs

Automation Platform Engineering

  • Built a governed low-code automation platform (Java, Python, REST) that lets business teams design, approve, and deploy workflows with audited access to enterprise systems.
  • Scaled it to 120+ reusable actions and 50+ production workflows across ~15 teams, cutting delivery from ~3 weeks to ~3 days and saving 300+ engineering hours.

Earlier engineering experience

AMC Networks

2020 to 2021

Senior Software Consultant · Client engagement

Embedded with support operations to ship a Teams virtual agent with NLU intent models that cut tickets 35%; automated ~60% of onboarding and offboarding access changes.

Yale University

2019 to 2020

Senior Software Consultant · Client engagement

Unified siloed asset tracking across ~5 departments into one platform for library and healthcare operations, plus a mobile app for ~40 field agents.

7-Eleven

2018 to 2019

Senior Software Consultant · Client engagement

Led tech-support modernization for 200+ retail stores, from workflow discovery with operations stakeholders through migration, rollout, and handoff.

USAA

2016 to 2018

Senior Software Consultant · Client engagement

Built integrations and automations for internal engineering teams, including service catalog intake automation that improved request handling ~40%.

03

Founder & creative AI

Applying the same practical AI systems thinking outside of enterprise engineering.

Svaram.ai

Founder, Side Venture · Oct 2025 to Present

An AI-assisted music studio for custom business anthems and promotional music, combining generative models with artist-in-the-loop creative direction to produce commercially usable tracks.

AI-enabled production workflows
Music generationStem separationVocal isolationKaraoke creationPost-production automation

Regionly

getregionly.com

AI-powered competitive intelligence product for local businesses: benchmarks each customer against nearby competitors and delivers localized market insights and actionable recommendations. 7 restaurant customers live.

04

Technical skills

AI Engineering

AI AgentsLangGraphLangChainMCPRAGLLM EvaluationContext EngineeringModel RoutingGuardrailsAI Security TestingLangfuseMLflowFine-tuning

Models & Inference

ClaudeQwenAWS BedrockSageMakerHugging FacevLLMOllamallama.cppSelf-Hosted GPU InferenceHybrid Local & CloudLatency & Cost Optimization

Data & AI Platforms

BigQuerydbtClickHouseSemantic LayersData ModelingPostgreSQLOpenSearchEnterprise Knowledge SystemsAnalytics Data Products

Software & Cloud

PythonTypeScriptGoJavaSQLFastAPIReactREST APIsGCPAWSVercelDockerCI/CD

Education

M.S. in Computer Science

Northwest Missouri State University · Missouri

2014 to 2015

B.E. in Computer Science

Vasavi College of Engineering · Hyderabad, India

2010 to 2014
06 / Contact

Let's build AI systems that work in production.

Open to AI roles, from building end-to-end AI platforms to forward-deployed delivery embedded with your team. Reach out and let's talk.