Artificial Intelligence Consultant

Softkeys LLC; Dallas (TX); Sur place; USD 120 000 - 170 000; Plein temps

Résumé du poste

Softkeys LLC seeks a skilled AI/ML engineer to advance transformer models and LLM-based workflows. You will implement MCP-based pipelines, utilize vector databases and RAG patterns, and collaborate with teams using LangChain, Semantic Kernel, and Copilot Studio.

The role emphasizes Python and enterprise language proficiency, cloud deployments, CI/CD, and governance for responsible AI, with a strong focus on experimentation, observability, and cost optimization.

Qualifications

• Hands-on with transformer architectures and modern LLMs.
• Experience with Model Context Protocol (MCP).
• Proficiency in Python; Java or another enterprise language.
• Experience with cloud platforms (Azure, AWS, GCP) and DevOps tools.
• Familiarity with vector DBs and RAG architectures.
• Ability to design, run and interpret A/B tests and KPIs.
• Knowledge of governance, observability, and drift detection for AI.
• Experience with CI/CD pipelines and RESTful API patterns.

Responsabilités

• Experimentation and measurement: A/B testing and KPI instrumentation.
• Operational analytics to monitor model performance and usage.
• Develop governance frameworks and controls for responsible AI.
• Maintain observability, cost optimization, and drift detection post-deployment.
• Design and implement vector search and RAG workflows.
• Collaborate with teams using frameworks like LangChain or Semantic Kernel.
• Implement tool-calling patterns with OpenAI/Anthropic interfaces.
• Contribute to cloud-native AI software development and DevOps processes.

Connaissances

Transformer architectures

LLM knowledge

Prompt engineering

Python proficiency

Java proficiency

OO design

A/B testing

KPI instrumentation

Agile/Scrum

Cloud platforms

CI/CD pipelines

RESTful APIs

DevOps tooling

GIT/GitHub

Observability/Monitoring

Cost optimization

Drift detection

Governance for AI

RAG architectures

Outils

Semantic Kernel

LangChain/LangGraph

Microsoft Copilot Studio

OpenAI tool-calling patterns

Anthropic tool-calling patterns

Pinecone

FAISS

Weaviate

Chroma

GitHub Copilot

Cursor

Claude Code

Description du poste

• Practical understanding of transformer architectures and how modern LLMs work.
• Hands-on experience with MCP (Model Context Protocol).
• Agentic orchestration using frameworks such as Semantic Kernel, LangChain/LangGraph, Microsoft Copilot Studio, OpenAI/Anthropic tool-calling patterns, or equivalent.
• Prompt engineering: systematic prompt design, few-shot learning, chain-of-thought, and prompt optimization for foundation models.
• Vector databases (e.g., Pinecone, FAISS, Weaviate, Chroma) and RAG architecture patterns.
• LLM evaluation methods, including LLM-as-a-judge, automated benchmarking, and regression testing of model outputs.
• Post-deployment model maintenance: observability, monitoring, cost optimization, and drift detection.
• Developing and implementing governance frameworks and controls for responsible AI.

Experimentation and measurement:

• A/B testing, KPI instrumentation, and operational analytics.
• Strong Python proficiency; working knowledge of Java or another enterprise language.
• Object-oriented design techniques and principles.
• Cloud platforms (Azure, AWS, or GCP) and cloud-native development patterns.
• CI/CD pipelines and DevOps tools: Git, GitHub, Jenkins, ADO Pipelines, or equivalent.
• RESTful API design and integration patterns (JSON, microservices).
• Agile methodologies such as Scrum.
• Microsoft Office tools (Project, Excel, Word, PowerPoint).
• Familiarity with AI-assisted development tools (GitHub Copilot, Cursor, Claude Code) is a plus