I'm a software engineer and researcher focused on AI reliability, distributed systems, and functional programming. I build infrastructure for LLM research on the Elixir/BEAM platform.
I'm the creator of the Crucible Framework, a platform for conducting reproducible experiments on large language model reliability, built on Elixir/OTP.
Key Goal: Building towards 99%+ LLM reliability through ensemble voting and request hedging, with comprehensive statistical testing and transparent causal reasoning chains.
All published under the @North-Shore-AI organization:
| Library | Description | Stars |
|---|---|---|
| crucible_framework | Documentation hub & research framework |  |
| crucible_bench | Statistical testing & analysis (15+ tests, effect sizes, power analysis) |  |
| crucible_ensemble | Multi-model voting strategies for improved reliability |  |
| crucible_hedging | Request hedging for latency reduction |  |
| crucible_trace | Causal reasoning chain logging for LLM transparency |  |
| crucible_datasets | Unified interface to benchmark datasets (MMLU, HumanEval, GSM8K) |  |
| crucible_telemetry | Research-grade instrumentation & metrics collection |  |
| crucible_harness | Automated experiment orchestration & reporting |  |
| Library | Description | Stars |
|---|---|---|
| crucible_adversary | Adversarial testing & robustness evaluation framework |  |
| crucible_xai | Explainable AI tools (LIME, SHAP, feature attribution) |  |
| ExDataCheck | Data validation & quality library for ML pipelines |  |
| ExFairness | Fairness & bias detection library for AI/ML systems |  |
| LLMGuard | AI firewall & guardrails for LLM-based applications |  |
Tech Stack: Elixir, OTP, BEAM VM, Telemetry Research Areas: LLM reliability, ensemble methods, tail latency optimization, statistical testing Status: Active development, v0.1.0 released
- json_remedy ⭐ 20 - A practical, multi-layered JSON repair library for Elixir that intelli…
- axon ⭐ 19 - Axon: Elixir-powered AI agent orchestration, built on the battle-teste…
- gemini_ex ⭐ 15 - Elixir Interface / Adapter for Google Gemini LLM, for both AI Studio a…
- ds_ex ⭐ 14 - DSPEx - Declarative Self-improving Elixir | A BEAM-Native AI Program O…
- foundation ⭐ 10 - Elixir infrastructure and Observability Library
- ex_dbg ⭐ 9 - State-of-the-Art Introspection and Debugging System for Elixir/Phoenix…
- snakepit ⭐ 8 - High-performance, generalized process pooler and session manager for e…
- sinter ⭐ 8 - Unified schema definition, validation, and JSON generation for Elixir
- exdantic ⭐ 8 - A powerful, flexible schema definition and validation library for Elix…
- DSPex ⭐ 8 - Declarative Self Improving Elixir - DSPy Orchestration in Elixir
- arsenal_plug ⭐ 2 - Phoenix/Plug adapter for Apex Arsenal framework
- claude_agent_sdk ⭐ 0 - Elixir SDK for Claude AI Agent API - Renamed from claude_code_sdk_elix…
- playwriter ⭐ 6 - Elixir WSL-to-Windows browser integration
- pipeline_ex ⭐ 6 - Claude Code + Gemini AI collaboration orchestration tools
- perimeter ⭐ 6 - Elixir Typing Mechanism
- jules_ex ⭐ 0 - Elixir client SDK for the Jules API - orchestrate AI coding sessions
- superlearner ⭐ 5 - OTP Supervisor Educational Platform
- mabeam ⭐ 4 - Multi Agent BEAM
- elixir_scope ⭐ 4 - Revolutionary AST-based debugging and code intelligence platform for E…
- ALTAR ⭐ 4 - The Agent & Tool Arbitration Protocol
- supertester ⭐ 3 - A battle-hardened testing toolkit for building robust and resilient El…
- sandbox ⭐ 3 - Isolated OTP application management system for Elixir/Erlang
- cluster_test ⭐ 3 - Distributed Erlang/Elixir test cluster management via Mix tasks
- cf_ex ⭐ 3 - Elixir libraries for Cloudflare edge computing services. Battle-tested…
- arsenal ⭐ 3 - Metaprogramming framework for automatic REST API generation from OTP o…
- apex_ui ⭐ 3 - Web UI for Apex OTP supervision and monitoring tools
- apex ⭐ 3 - Core Apex framework for OTP supervision and monitoring
- ElixirScope ⭐ 3 - AI-Powered Execution Cinema Debugger for Elixir/BEAM
- AutoElixir ⭐ 3 - AI Multi Agent Swarms in Elixir
- youtube_audio_dl ⭐ 0 - Download high-quality audio from YouTube as MP3 files using Elixir. Fe…
- tools ⭐ 0 - Elixir repository
- ex_cloudflare_phoenix ⭐ 0 - Cloudflare Durable Objects and Calls for Phoenix Framework
- Citadel ⭐ 0 - The command and control layer for the AI-powered enterprise
- Assessor ⭐ 0 - The definitive CI/CD platform for AI Quality.
- AITrace ⭐ 0 - The unified observability layer for the AI Control Plane
- crucible_trace ⭐ 0 - Structured causal reasoning chain logging for LLM transparency
- crucible_telemetry ⭐ 0 - Advanced telemetry collection and analysis for AI research
- crucible_hedging ⭐ 0 - Request hedging for tail latency reduction in distributed systems
- crucible_harness ⭐ 0 - Experimental research framework for running AI benchmarks at scale
- crucible_framework ⭐ 0 - CrucibleFramework: A scientific platform for LLM reliability research …
- crucible_ensemble ⭐ 0 - Multi-model ensemble voting strategies for LLM reliability
- crucible_datasets ⭐ 0 - Dataset management and caching for AI research benchmarks
- crucible_bench ⭐ 0 - Statistical testing and analysis framework for AI research
- crucible_adversary ⭐ 0 - Adversarial testing & robustness evaluation framework
- crucible_xai ⭐ 0 - Explainable AI tools (LIME, SHAP, feature attribution)
- ExDataCheck ⭐ 0 - Data validation & quality library for ML pipelines
- ExFairness ⭐ 0 - Fairness & bias detection library for AI/ML systems
- LLMGuard ⭐ 0 - AI firewall & guardrails for LLM-based applications
Languages: Elixir, Erlang, Python, JavaScript/TypeScript, Rust Frameworks: Phoenix, OTP, FastAPI, React Specialties:
- Distributed systems & fault tolerance
- AI/LLM infrastructure & reliability
- Functional programming & metaprogramming
- Statistical analysis & experimental design
- Developer tools & productivity
Platforms: BEAM VM, AWS, GCP, Cloudflare Workers, Edge Computing
Research: LLM reliability through ensemble methods and statistical testing
Building: AI infrastructure on Elixir/OTP
Learning: Advanced OTP patterns, distributed systems optimization
Growing: The Crucible framework ecosystem
- GitHub: @nshkrdotcom
- Organization: @North-Shore-AI
"Build infrastructure that researchers and engineers actually want to use. Make reliability measurable. Make experiments reproducible. Make the BEAM shine for AI workloads."
Collaboration on Elixir AI tooling
Consulting for distributed systems & AI infrastructure
Speaking about LLM reliability, Elixir/OTP, or functional programming
Open source contributions - PRs welcome on any project!
Fun fact: All Crucible framework commits are co-authored with Claude AI!
Last updated: 2025-10-10