App LogoApp name
RT

Ryan Thayil

Open to work0 years experience

Software Developer

Bengaluru, KarnatakaTarget Roles: Backend Engineer • Full-Stack Developer • Frontend Specialist

AI engineer with demonstrated ability to design and build agentic systems from first principles.

GitHubLinkedIn
Resume
Email

Standing Rank

Rank Not Available

Developer Badges

Badges Pending

Skills & Technologies

22 skills
pythonllm integrationagentic workflow designmulti-step orchestrationtool callingstructured outputprompt engineeringrag patternsreinforcement learningmulti-agent systemspartial observabilitystate representation designadversarial testingyoloopencvreal-time inference pipeline designedge deploymentjavascriptsqlrest apisgitagile delivery

Work Experience

Analyst Intern

KPMG India

Jan 2026 - Present Bengaluru
  • Designed and implemented automated workflows and intelligent routing logic in a production enterprise environment across ITSM, CBS Catalog, and Custom Apps — experience with multi-step, conditionally-branching system design.
  • Worked in Agile sprint cycles with well-defined intake, build, test, and deployment gates — the kind of rigorous, incremental engineering discipline required for building complex AI systems reliably.
  • Engaged directly with stakeholders to reason about requirements from first principles and translate ambiguous needs into working systems.

Artificial Intelligence Intern

NIVID Innovative Solutions Ltd.

Apr 2025 - Jun 2025 Bengaluru
  • Designed and built an agentic AI pipeline — camera feed → YOLO object detection → context extraction → LLM prompt → speech response — a real perception-action loop operating in a partially observable environment.
  • Engineered adversarial robustness into the pipeline: defined failure modes, built fallback mechanisms, and tested system behaviour under degraded input conditions.
  • Optimised for real-time decision-making under constrained compute — experience balancing reasoning quality and latency in a live-inference setting.

Web Development Intern

National Institute of Hydrology (NIH)

Apr 2024 - May 2024 Roorkee
  • Full-stack application engineering with backend API design — foundational systems experience underpinning more complex AI architecture work.

Projects

Voice Assistant & Object Detection — Humanoid Robot

LLMComputer Vision
  • Architected a multi-stage agentic system from scratch — sensor input, state representation, context extraction, LLM-based reasoning, and action generation — without a framework or playbook.
  • Confronted and solved the partial observability problem in a real deployment: the agent had to reason about its environment from incomplete visual input and construct meaningful context for the LLM.
  • Built interpretability into the pipeline — structured prompting and output formatting ensured the agent's reasoning was auditable and its actions traceable.

Sports Attendance Tracker

MLLLM
  • Integrated an AI-powered attendance prediction module using ML classification to flag absenteeism patterns and generate automated alerts for coaching staff.
  • Built a natural language query interface using LLM integration, enabling coaches and admins to retrieve attendance insights through plain-English prompts instead of manual filtering.
  • Designed an AI-driven anomaly detection layer that identified irregular attendance trends and surfaced actionable recommendations, reducing manual review time significantly.

Leaderboard Standings

Leaderboard Position Pending

Global test scores, peer standing percentiles, and algorithm leaderboard ranks are updated dynamically.

Assessment Highlights

Assessments Not Completed

Coding evaluations, system assessment results, and conceptual score badges will appear here after taking a test.

AI Collaboration Score

AI Collaboration Score Pending

Developer coding behavior, assistant cooperation, and AI pair-programming indicators are evaluated during live coding sessions.

Role Compatibility Profile

Role Compatibility Analysis Pending

Custom matching reports, candidate role compatibility percentiles, and core engineer strength profiles are processed once conceptual code screenings are complete.

Achievements

Achievements Not Earned

Special rewards, developer badges, system recognition certificates, and conceptual milestones will display here.

About Details

Professional Bio

AI engineer with demonstrated ability to design and build agentic systems from first principles. Proficient in Python, LLM integration, multi-step orchestration, and adversarial reasoning design. Drawn to hard, open-ended AI architecture problems.

B.Tech., Computer Science (AIML) in Computer Science (AIML)

Christ University ( - 2026)

Languages: English, Hindi
Email: Locked