SkillForge

Design retrieval-augmented generation systems with chunking, ranking, citation, and context-budget discipline that hold up in production.

CodexClaude CodeKimi Codeorchestrator-mcp

Allocate work across local, cloud, and premium models so teams maximize capability coverage per dollar and per latency budget.

CodexClaude CodeKimi Codeorchestrator-mcp

Reshape sprawling repositories and briefs into stable context lanes, memory checkpoints, and retrieval boundaries for long-horizon agent work.

CodexClaude CodeKimi Codeorchestrator-mcp

Tune provider routing policy for quality, cost ceilings, and fallback behavior across multiple model subscriptions.

CodexClaude CodeKimi Codeorchestrator-mcp

Build eval cases that expose fabricated citations, brittle reasoning chains, and ungrounded tool usage before they hit real workflows.

CodexClaude CodeKimi Codeorchestrator-mcp

Tune timeout, retry, and concurrency budgets across multi-model routes so orchestration stays fast without silent quality collapse.

CodexClaude CodeKimi Codeorchestrator-mcp

Improve chunking, metadata, and ranking design so agent answers stay grounded under larger repositories and longer tasks.

CodexClaude CodeKimi Codeorchestrator-mcp

Design robust communication protocols for agent systems with message schemas, serialization, and delivery guarantees

CodexClaude CodeKimi Codeorchestrator-mcp

Manage complete agent lifecycles from initialization through graceful shutdown with health monitoring, scaling, and resource optimization

CodexClaude CodeKimi Codeorchestrator-mcp

Design short-term, long-term, and episodic memory layers for agents without turning retrieval into an unbounded context leak.

CodexClaude CodeKimi Codeorchestrator-mcp

Optimize large-scale agent swarms for emergent problem-solving with dynamic task allocation and collective intelligence patterns

CodexClaude CodeKimi Codeorchestrator-mcp

Build evaluation loops for AI systems with benchmark sets, rubric design, judge calibration, and human-review anchors.

CodexClaude CodeKimi Codeorchestrator-mcp

Design comprehensive oversight systems for AI agents with monitoring, intervention, and escalation protocols

CodexClaude CodeKimi Codeorchestrator-mcp

Design and execute comprehensive safety evaluations for AI systems with red-teaming, adversarial testing, and safety metric frameworks

CodexClaude CodeKimi Codeorchestrator-mcp

Implement constitutional AI principles with self-critique, revision loops, and principled response generation

CodexClaude CodeKimi Codeorchestrator-mcp

Optimize context window usage for RAG systems with intelligent chunking, relevance ranking, and dynamic context assembly

CodexClaude CodeKimi Codeorchestrator-mcp

Build embedding pipelines with retrieval-aware chunking, vector index strategy, and similarity quality that can be measured.

CodexClaude CodeKimi Codeorchestrator-mcp

Design effective few-shot prompts with example selection, formatting, and optimization for consistent high-quality outputs

CodexClaude CodeKimi Codeorchestrator-mcp

Create fine-tuning workflows with dataset preparation, evaluation baselines, and rollback-ready deployment checkpoints.

CodexClaude CodeKimi Codeorchestrator-mcp

Design robust function calling systems with schema validation, error handling, and multi-step tool orchestration

CodexClaude CodeKimi Codeorchestrator-mcp

Design and implement GraphRAG systems that leverage knowledge graphs for enhanced retrieval and multi-hop reasoning

CodexClaude CodeKimi Codeorchestrator-mcp

Build tree-structured agent hierarchies for complex decision-making with clear authority chains and delegation patterns

CodexClaude CodeKimi Codeorchestrator-mcp

Design and implement hybrid search systems combining dense, sparse, and keyword retrieval for optimal relevance

CodexClaude CodeKimi Codeorchestrator-mcp

Optimize model serving with batching, quantization, streaming, and deployment-aware latency budgets that preserve quality.

CodexClaude CodeKimi Codeorchestrator-mcp

Build knowledge graphs from unstructured data with entity extraction, relationship identification, and graph construction

CodexClaude CodeKimi Codeorchestrator-mcp

Design multi-layer caching strategies for LLM inference with semantic cache, prompt cache, and response cache optimization

CodexClaude CodeKimi Codeorchestrator-mcp

Compose sophisticated LLM chains with conditional routing, parallel execution, and state management

CodexClaude CodeKimi Codeorchestrator-mcp

Integrate hosted and local LLM providers with fallback, rate limiting, and spend-aware routing that remains debuggable in production.

CodexClaude CodeKimi Codeorchestrator-mcp

Design intelligent load balancing for LLM inference with request routing, session affinity, and dynamic capacity management

CodexClaude CodeKimi Codeorchestrator-mcp

Design and implement production-grade LLM serving infrastructure with optimal throughput, latency, and cost efficiency

CodexClaude CodeKimi Codeorchestrator-mcp

Build comprehensive observability for LLM systems with tracing, metrics, logging, and cost analytics

CodexClaude CodeKimi Codeorchestrator-mcp

Design sophisticated rate limiting for LLM APIs with token-based quotas, tiered limits, and burst handling

CodexClaude CodeKimi Codeorchestrator-mcp

Build comprehensive testing frameworks for LLM applications with unit tests, integration tests, and evaluation metrics

CodexClaude CodeKimi Codeorchestrator-mcp

Put model versioning, experiment tracking, drift detection, and rollback policy around production AI systems.

CodexClaude CodeKimi Codeorchestrator-mcp

Design and orchestrate complex multi-agent systems where specialized agents collaborate to solve problems beyond single-agent capabilities

CodexClaude CodeKimi Codeorchestrator-mcp

Integrate text, vision, audio, and document intelligence into one application surface with graceful modality-aware fallbacks.

CodexClaude CodeKimi Codeorchestrator-mcp

Design system prompts, prompt contracts, and eval-backed example sets that improve LLM reliability without hiding failure modes.

CodexClaude CodeKimi Codeorchestrator-mcp

Build comprehensive evaluation frameworks for RAG systems with retrieval metrics, generation metrics, and end-to-end assessment

CodexClaude CodeKimi Codeorchestrator-mcp

Design robust reward functions and evaluation frameworks that prevent reward hacking and specification gaming

CodexClaude CodeKimi Codeorchestrator-mcp

Design robust structured output systems with JSON schemas, validation, and parsing for reliable data extraction

CodexClaude CodeKimi Codeorchestrator-mcp

Test and validate AI system alignment with organizational and societal values through systematic evaluation frameworks

CodexClaude CodeKimi Codeorchestrator-mcp

AI/ML Engineering