AI & Security Engineering · Cisco · Bengaluru

Manohar Eldhandi

Software Engineer

At Cisco, I build Python agentic-AI workflows for code-security reviews. The security-compliance tooling is used by 50+ engineers across 4 product teams and has reduced manual review effort by about 70%.

eldhandimanohar@gmail.com Bengaluru, India

Experience

Oct 2025 - Present Bengaluru

Software Engineer · Cisco

  • Designed and built 3 Python agentic-AI workflows that generate structured JSON for code-security reviews with LLM APIs and prompt engineering, cutting manual review effort by about 70% across 4 product teams.
  • Used LangChain to wrap 2 LLM providers, Codex and GitHub Copilot, behind one chat interface and LangGraph to orchestrate agents without provider-specific workflow changes.
  • Integrated multi-provider MCP tool servers for security data and Jira into LangGraph agents, then designed reusable Agent Skills for 50+ engineers across 4 teams.
  • Assisted with a RAG grounded-retrieval layer and code graph for 20K+ source files; 50+ parallel workers feed an 11-stage pipeline that cut model calls 10x.
  • Built Playwright UI tests at 97% coverage and executed 736 pytest tests across 10+ CI/CD releases, reducing manual QA by 60%.

Projects

01

OnTheWay ↗

Java 17 · Spring Boot · React · GraphQL · Kafka · Elasticsearch

Route-aware pickup and reservation marketplace with orders timed to customer arrival.

  • Built a Java and Spring Boot marketplace with 47 REST endpoints plus 3 GraphQL operations, JWT role-based security, MySQL with Flyway, and Elasticsearch search.
  • Added live marketplace updates through Kafka and WebSocket event processing, with Docker and Kubernetes delivery assets.
  • Validated 85 JUnit tests and a developer-machine 1,000-user load baseline sustaining 730 sessions per second at p99 884 ms with zero failures.
02

Carivyo-AI ↗

React · TypeScript · FastAPI · Python · SQLite · LLM APIs

Local-first career-intelligence platform for evidence profiles, role ranking, and controlled application preparation.

  • Built evidence profiles and role ranking with 2 model runtimes, a 27-check ATS diagnostic, and approval gates that stop unsupported generation when evidence changes.
  • Integrated 4 official hiring-system connectors and 120 curated company boards with structured outputs, eligibility filters, and explicit provenance.
  • Protected the local-first workflow with redacted logs, layered prompt-injection defenses, and user-controlled application handoff.

Skills

AI

AI & Security Engineering

Build agentic security workflows with grounded context, structured outputs, reusable tools, and model orchestration that teams can inspect.

Agentic AIAI AgentsAgent SkillsMulti-Agent OrchestrationSecurity AutomationMCPLangGraphLangChainLLM APIsPrompt EngineeringRAGVector RetrievalSemantic SearchContext Engineering
API

Full-Stack Systems

Build secure APIs, stateful service layers, event-driven backends, and React interfaces that can be tested, reviewed, and extended cleanly.

JavaPythonSpring BootFastAPIREST APIsGraphQLWebSocketsSpring SecurityAPI DesignJWTSQLMySQLFlywaySQLiteKafkaElasticsearchReactTypeScriptJavaScriptHTMLCSS
ML

Machine Learning

Handle practical ML pipelines from preprocessing and feature engineering to model comparison, probability scoring, evaluation, and product integration.

scikit-learnPandasNumPyXGBoostFeature engineeringModel evaluationClassificationProbability scoring
QA

Reliability & Tools

Use automated tests, logging, performance checks, cloud tooling, and release automation to keep systems traceable and regression-safe.

JUnit 5pytestPlaywrightAPI TestingAutomated TestingLoggingPerformance OptimizationAWS FundamentalsAzure BasicsDockerKubernetesGitHub ActionsCI/CDGitLinux

Achievements

01
Competitive Programming

Reached Codeforces Master 2141 and CodeChef 4-star 1893, with global ranks 32 in Starters 239, 140 in Educational Codeforces Round 191, and 295 in Codeforces Round 1100.

Profile ↗
02
LER_DSA · Open Source

Authored a 20-module Java and Python roadmap adopted by 500+ juniors at CMR Institute of Technology, with per-module interview-preparation tracking.

Repository ↗
03
Cisco Webex Playtime Hackathon

Placed top 35 of 2,000+ teams, within the top 2%, for AI security-compliance automation.

Cisco
04
Smart Interviews

Mentored 150+ students in Java and data structures, improved average assessment scores by 40%, and earned a Mentor Certificate.

Certificate ↗
05
Amazon ML Summer School 2024

Selected in the top 1% of 50,000+ applicants and completed training in supervised and unsupervised learning, NLP, deep learning with TensorFlow and PyTorch, and model evaluation.

Certificate ↗
06
Certifications

Obtained CCNA, Cisco AI Technical Practitioner, and AWS Cloud Fundamentals.

View all ↗

Education

Dec 2021 - Jul 2025 CGPA 8.5 / 10

B.Tech · Computer Science and Engineering, AI & ML

CMR Institute of Technology, Hyderabad · Affiliated to JNTU Hyderabad

Profiles

LeetCode · Problem-solving profile ↗ Codeforces · Master 2141 ↗ CodeChef · 4-star 1893 ↗