Senior AI Infrastructure & Systems Engineer. Building low-latency LLM serving runtimes, distributed observability (OTel/Prometheus), and enterprise agentic platforms.

llm-production-engineering - Field notes from building AI systems in production since 2019. The ops side of LLM serving: cost tracking, eval-driven deployment, capacity planning, observability, incident playbooks, and decision frameworks. Maps directly to my day job at Airbnb.

• Multi-tenant OTel cost tracking for LLM platforms (per-request, per-team, per-product attribution)
• Prefix-caching telemetry and cache-miss detection across Bedrock, OpenAI, Anthropic, vLLM
• Redis token bucket budgets for multi-tenant rate limiting
• Eval-driven deployment: 23+ agent versions, 1,690 versioned ground-truth samples, dual-model A/B testing

• Role: Senior AI Infrastructure & Systems Engineer at Airbnb. I own end-to-end architecture and production rollout of the BPI Virtual Analyst platform - a multi-model GenAI orchestration system abstracting 30+ foundation models (AWS Bedrock, OpenAI, Anthropic Claude, vLLM) behind FacadeDriver with routing, retry, fallback, and graceful degradation. Platform processes 10K rows per run and 40MB uploads with PII-safe inference, serving 55+ analysts across 4 partner engineering teams.
• Streaming & Batch: Owned architecture and production operation of Kafka pipelines sustaining 4M req/min at Southwest Airlines with idempotent partition-keyed consumers, DLQ, and backpressure handling. Cut on-call MTTR from 45 to 12 minutes (73% reduction). Owned batch ETL on Databricks and Azure Data Factory at Shell with PySpark, Spark SQL, and Hive/Trino.
• Observability: OpenTelemetry collectors, Loki tracing (prompt, tool call, retrieval quality), Datadog, Grafana, drift detection, post-incident review. The same stack I open-source on in LangChain and LiveKit.
• Research: Published across Cambridge Scholars Publishing (2 book chapters, 2025), IEEE Xplore, SPE ADIPEC 2022 (SPE-210986-MS), and ResearchGate. AI safety, state space models, and ML infrastructure.
• Open to: AI infrastructure consulting, advisory, and conference speaking (NVIDIA GTC, AI Engineer Summit, Ray Summit, Data+AI Summit, QCon, AWS re:Invent customer stage).
• Portfolio: sailikhith.me | Articles: sailikhithk.com | AI-readable: sailikhith.me/llm.txt

# Sai Likhith Kanuparthi
> Senior AI Infrastructure & Systems Engineer @ Airbnb.
> LLM serving runtimes, distributed observability (OTel/Prometheus), enterprise agentic platforms.
> Kafka 4M req/min | vLLM | Bedrock | FacadeDriver (30+ model orchestration).

## Links
- Portfolio: https://sailikhith.me/
- Blog: https://sailikhithk.com/
- LinkedIn: https://www.linkedin.com/in/sailikhithk/
- AI-readable profile: https://sailikhith.me/llm.txt
- AI-readable portfolio: https://sailikhith.me/llms.txt

## Open-Source AI/ML Repositories
- https://github.com/sailikhithk/llm-production-engineering (LLM ops: cost tracking, eval-driven deploy, observability)
- https://github.com/sailikhithk/Project-X (Multi-agent RAG framework with tool-augmented retrieval)
- https://github.com/sailikhithk/Tags-recommender-system-for-community-forums (BERT/MLP tag recommender for forum posts)
- https://github.com/sailikhithk/CreditCardFraudDetectionUsingKafka (Real-time fraud detection with Kafka streaming)
- https://github.com/sailikhithk/Adaptive-Multi-Robot-Path-Planning (Multi-robot path planning with RL)
- https://github.com/sailikhithk/Intelligent-Document-Understanding (OCR + NLP document classification)
- https://github.com/sailikhithk/Smart-Healthcare-Assistant (Clinical NLP and decision support)
- https://github.com/sailikhithk/Neural-Network-From-Scratch (NumPy-only NN implementation for teaching)

## Production Work (Airbnb)
- BPI Virtual Analyst: multi-model GenAI orchestration (30+ foundation models via FacadeDriver)
- Kafka pipelines: 4M req/min, idempotent consumers, DLQ, MTTR 45 -> 12 min
- Eval harness: 23+ agent versions, 1,690 ground-truth samples, dual-model A/B testing
- Observability: OpenTelemetry, Loki, Datadog, Grafana, drift detection

## Research
- IEEE Xplore: https://ieeexplore.ieee.org/abstract/document/11004721
- SPE ADIPEC 2022: https://doi.org/10.2118/210986-MS
- Cambridge Scholars Publishing (2 book chapters, 2025)

## Certifications
- AWS Solutions Architect Professional
- AWS Developer Associate
- AWS Machine Learning Specialty
- Azure Data Scientist Associate (DP-100)
- Google Cloud Professional Data Engineer

Active contributor to LiteLLM (BerriAI), the unified LLM proxy used in production at Airbnb and across the AI industry.

Fixes span the Vertex AI provider, batch billing lifecycle, and guardrails metadata handling for the Anthropic-style /v1/messages endpoint.

Contributing upstream to the LLM tooling I use in production at Airbnb. 8 PRs across 5 repos in August 2026.

Focus areas: LLM cost tracking, eval metrics, provider compatibility, guardrails. Maps directly to my day job building FacadeDriver (30+ LLM orchestration) and eval harnesses (23+ agent versions, 1,690 ground-truth samples) at Airbnb.

Also certified in: AWS Solutions Architect Associate · Google Cloud Professional Data Engineer · Oracle Database 12c Administrator · Oracle Java SE 8 Programmer

Portfolio: sailikhith.me · Blog: sailikhithk.com · AI-readable profile: sailikhith.me/llm.txt