# Shreyas Kulkarni

> MS CS Northeastern, Boston | Agentic AI Engineer | LLM Systems | AWS Bedrock | LangGraph | RAG Pipelines | Software Engineer | DevOps | Docker Kubernetes MERN MEAN

Location: Boston, Massachusetts, United States
Profile: https://flows.cv/shreyaskulkarni

I build autonomous AI systems that actually work in production.

As an Agentic AI Engineer with 5+ years of experience, I specialize in designing multi-agent architectures that move beyond chatbots into real, measurable business automation. My work sits at the intersection of LLM engineering, cloud infrastructure, and production reliability — turning foundation models into orchestrated agent teams that reason, act, and self-correct at enterprise scale.

What I do day-to-day:

I architect multi-agent workflows using LangGraph, LangChain, and CrewAI — building systems where specialist agents collaborate through ReAct loops, self-critique chains, and human-in-the-loop validation. I design and optimize RAG pipelines end-to-end: chunking strategies, embedding model selection, hybrid search (dense + sparse), reranking, and structured Pydantic outputs — achieving 92% retrieval accuracy across production semantic search systems. I deploy these systems on AWS using Amazon Bedrock (Claude, Titan), Lambda, Step Functions, EKS, and EventBridge with full observability through CloudWatch tracing and spans.

The results speak for themselves: 65% reduction in manual intervention through autonomous task planning, 50% faster data annotation via agentic human-in-the-loop pipelines, 89% recall@10 on domain-specific retrieval benchmarks, and 99.9% uptime on serverless agentic backends processing 10,000+ daily inference requests.

My technical depth spans the full agentic AI stack:

→ Agent Frameworks: LangGraph, LangChain Agents, CrewAI, Multi-Agent Orchestration, Tool Calling, Memory Management, Guardrails, MCP (Model Context Protocol)
→ LLM Engineering: Prompt Engineering, RAG Pipelines, Hybrid Search, Rerankers, Structured Outputs, PII Redaction, LLM Evaluation, Hallucination Detection
→ AWS & Cloud: Amazon Bedrock, Lambda, Step Functions, EKS, EventBridge, CloudWatch, SQS, API Gateway, S3, IAM, Terraform, CloudFormation
→ Vector Databases: Pinecone, FAISS, ChromaDB, Semantic Search, Embedding Models, Chunking & Indexing Strategies
→ ML & NLP: Classification, Regression, NLP, Anomaly Detection, Feature Engineering, spaCy, MLOps
→ Full-Stack: Python, FastAPI, Java, Spring Boot, Node.js, ReactJS, TypeScript, REST APIs, GraphQL
→ DevOps: Docker, Kubernetes, GitHub Actions, Terraform, Jenkins, CI/CD

Before agentic AI, I spent 3+ years building cloud-native microservices processing 50,000+ daily transactions for enterprise healthcare billing at SS&C Technologies and Infosys — giving me the production engineering discipline that most AI engineers lack.

## Work Experience
### AI Engineer @ Northeastern University Boston @ Northeastern University College of Engineering
Jan 2025 – Jan 2025 | Boston, Massachusetts, United States
Designed and implemented multi-agent research prototype using LangGraph for automated literature review and synthesis —
agents autonomously retrieve papers, extract key findings, identify contradictions, and generate structured summaries with
citation provenance.
• Built experimental RAG evaluation framework benchmarking chunking strategies (fixed-size, semantic, document-aware),
embedding models (OpenAI, Cohere, BGE), and reranking approaches across 5 domain-specific corpora; published internal findings
on optimal retrieval configurations achieving 89% recall@10.
• Developed Bedrock-integrated agentic pipeline for research data annotation, using structured Pydantic outputs and human-in-the-
loop validation to generate high-quality labeled datasets — reducing annotation time by 50% compared to manual labeling
workflows.
• Implemented MCP (Model Context Protocol) server for connecting LLM agents to university research databases, enabling tool-use
grounded retrieval across 200K+ academic documents with semantic search and metadata filtering.
• Built evaluation harness for measuring agent reliability: task completion rates, hallucination detection, tool-call accuracy, and
reasoning chain quality across multi-step workflows — used to benchmark 4 LLM providers systematically.

### Software Engineer @ SS&C Technologies
Jan 2024 – Jan 2024 | Boston, Massachusetts, United States
• Architected production-grade agentic AI platform using LangGraph multi-agent workflows (specialist/reviewer/executor pattern),
enabling autonomous multi-step task planning and self-critique loops that reduced manual intervention by 65% across enterprise AI
pipelines.
• Implemented robust RAG pipelines with hybrid search (dense + sparse), custom chunking/indexing strategies, and Pinecone vector
database integrated with Amazon Bedrock (Claude, Titan), achieving 92% retrieval accuracy and citation-first structured outputs for
semantic search applications.
• Designed and enforced LLM guardrails including prompt/policy templates, structured JSON/Pydantic outputs, and allow/deny tool
lists to ensure auditability, safety, and reliability across 10,000+ daily AI inference requests.
• Built serverless agentic backend on AWS Lambda, Step Functions, and EventBridge; instrumented agents with CloudWatch metrics,
spans, and traces for full observability and audit trails — maintaining 99.9% uptime.
• Integrated multiple LLM providers (OpenAI, Anthropic Claude, Titan) through unified API architecture enabling seamless model
switching, reducing LLM inference costs by 30% while improving response quality.
• Engineered CI/CD pipelines with GitHub Actions and Terraform for automated deployment, reducing deployment cycle from 4 hours
to 15 minutes; developed ReactJS monitoring dashboard improving operational visibility by 40%.

### Senior Technology Analyst @ Infosys Ltd
Jan 2021 – Jan 2023 | Pune, Maharashtra, India
• Engineered cloud-native microservices on AWS (EKS, Lambda, RDS) processing 50,000+ daily transactions for enterprise
healthcare billing platform; implemented event-driven architecture with EventBridge and Step Functions reducing system latency
by 35%.
• Developed NLP-based data extraction pipeline using spaCy and rule-based classifiers to process unstructured medical billing
documents (EOBs, remittance advices), achieving 88% field-level extraction accuracy and reducing manual data entry by 45%.
• Built anomaly detection system for billing fraud identification using isolation forests and engineered features (claim frequency,
provider deviation scores, billing code patterns), flagging 3,200+ suspicious claims monthly with 91% precision.
• Designed RESTful APIs using Java/Spring Boot integrated with PostgreSQL RDS supporting 99.99% availability SLA; built ReactJS
frontends achieving 25% improvement in page load performance.
• Established automated testing frameworks achieving 85% code coverage, reducing production defects by 40%; delivered sprint
features 20% ahead of schedule collaborating with 12+ engineers and data scientists.

### Software Developer @ ITARIUM Technologies India Pvt. Ltd.
Jan 2020 – Jan 2020 | Pune, Maharashtra, India
Developed 20+ RESTful APIs for trading platform integration, processing $5M+ in daily transaction volume with sub-200ms response times
•
Created responsive web applications using Angular and JAVA, Spring Boo, serving 75K+ concurrent users during peak trading hours
•
Implemented automated testing frameworks using JUnit, Mockito, and Cucumber, achieving 92% code coverage and reducing production defects by 40%
•
Collaborated in Agile environment delivering 25+ features across 8 sprint cycles, consistently meeting 95% of committed story points
•
Designed UML system diagrams for 5 major system integrations, improving development team understanding and reducing implementation time by 30%

### Software Developer @ Bharati Robotic Systems
Jan 2019 – Jan 2019 | Pune
•
Architected and implemented identity management services supporting 15M+ monthly active users, reducing authentication failures by 42% while improving response times by 65%
•
Led migration of legacy authentication systems to scalable microservices architecture using Python and Kubernetes, resulting in 99.99% availability. Designed and deployed CI/CD pipelines with GitLab and Jenkins, reducing deployment time from 2 hours to 12 minutes and enabling 60+ weekly deployments
•
Implemented Infrastructure as Code using Terraform to provision and manage cloud resources across AWS and GCP, reducing infrastructure management time by 75%. Created comprehensive automated test suites that increased code coverage from 72% to 94%, decreasing production incidents by 61%
•
Mentored 4 junior engineers on DevOps best practices and security-focused development, resulting in a 35% improvement in code quality metrics

### Artificial Intelligence Engineer @ Indian Institute of Science (IISc)
Jan 2018 – Jan 2019 | Bangalore
• Engineered real-time monitoring platform for LLM-powered Azure Application InsightsStayed late voluntarily to help senior colleague debug complex React state management issue affecting user dashboard, learning advanced JavaScript concepts through hands-on problem-solving that accelerated my technical growth by months
• Took initiative to optimize slow-loading data visualization component that customers complained about, researching and implementing D3.js lazy loading techniques that improved page load time from 8 seconds to 1.2 seconds
• Participated in hiring interview for another junior developer despite being newest team member, providing valuable peer perspective that helped identify culture fit and resulted in successful long-term hire
• Organized team's first hackathon during COVID remote work transition, coordinating virtual collaboration tools and pizza delivery logistics for 15 people across 3 states, boosting team morale during challenging period

### Web Developer @ Self-employed
Jan 2016 – Jan 2019 | Pune
Led AI-powered document processing platform serving 500K+ enterprise users
•
Spearheaded emergency AI model migration during OpenAI service disruption, designing fallback architecture using multiple LLM providers (Azure OpenAI, Anthropic, Cohere) that maintained 99.8% service availability while other competitors experienced 3-day outages
•
Debugged critical memory leak in production chat assistant affecting 15K concurrent users during peak hours, implementing custom C# garbage collection optimization and Redis session management that eliminated 2AM escalations for the on-call team
•
Mentored junior engineer through complex RAG implementation, pair-programming vector database integration with Azure Cognitive Search, resulting in their successful first major feature release and promotion within 8 months
•
Advocated for accessibility compliance after customer feedback from visually impaired users, retrofitting React components with ARIA labels and keyboard navigation, achieving WCAG 2.1 AA certification and preventing potential $2M contract loss
•
Orchestrated seamless zero-downtime deployment during Black Friday traffic surge, coordinating with DevOps team to implement blue-green deployment strategy using Azure Container Instances, ensuring uninterrupted service for peak 50K concurrent users

### Software Developer @ COMPUTER HOME PRIVATE LIMITED
Jan 2018 – Jan 2018 | Pune, Maharashtra, India
I have  worked on Front end Development on Angular, & Apache Cordova Framework. I have developed an application for Maharashtra State Government, many other clients. I have a work experience of 8 months in Angular Application Development.

### Android App Development @ College Project
Jan 2017 – Jan 2017 | Manipal
Developed an Android app on Library database management.

### Cloud Computing @ Yagnot Technocrats
Jan 2016 – Jan 2016 | Pune, Maharashtra, India
Developed a web based Cloud project for secured storage of documents and data.


## Education
### Master's degree in Information Systems
Northeastern University

### Postgraduate Degree in ARTIFICIAL INTELLIGENCE & Machine Learning
Indian Institute of Science (IISc)

### Bachelor of Technology (B.Tech.) in Computer Science
Manipal Institute of Technology


## Contact & Social
- LinkedIn: https://linkedin.com/in/shreyaskulkarniprofile

---
Source: https://flows.cv/shreyaskulkarni
JSON Resume: https://flows.cv/shreyaskulkarni/resume.json
Last updated: 2026-03-28