Machine Learning Engineer
Incedo Inc.Full Description
Job Title- AI/ML Engineer – LLM & RAG Solutions
Location- Fort Mills, SC (Hybrid)
Experience- 3–6 years
Role Overview:
We are seeking a skilled AI/ML Engineer with hands-on experience building and deploying LLM-powered applications in production environments. The ideal candidate will have expertise in prompt engineering, model versioning, output validation, fallback mechanisms, and Retrieval-Augmented Generation (RAG) frameworks.
The role requires experience designing secure and scalable AI solutions with policy-based input/output controls, ensuring reliability, compliance, and high-quality AI responses.
Key Responsibilities
* Design, develop, and deploy LLM-based applications and AI features in production environments
* Build and optimize RAG (Retrieval-Augmented Generation) pipelines for enterprise use cases
* Implement:
* prompt engineering strategies
* prompt/version management
* response validation
* fallback and retry mechanisms
* Develop controlled generation workflows with:
* input filtering
* output moderation
* policy enforcement
* Integrate AI models with APIs, vector databases, and enterprise applications
* Collaborate with product, engineering, and data teams to deliver scalable AI solutions
* Monitor model performance, hallucinations, latency, and response quality
* Improve reliability, observability, and governance of AI systems
* Contribute to AI architecture, experimentation, and optimization initiatives
Required Skills & Qualifications
* 3+ years of experience building and deploying AI/ML solutions
* Hands-on experience shipping LLM features into production
* Strong expertise in:
* Prompt Engineering
* Prompt/Model Versioning
* Output Validation
* Fallback Handling
* Experience with RAG architectures and semantic retrieval systems
* Knowledge of policy-based AI controls for:
* input validation
* output filtering
* safe AI responses
* Strong programming skills in Python
* Experience with:
* LangChain / LlamaIndex
* OpenAI / Anthropic / Gemini APIs
* Vector databases (Pinecone, Weaviate, Chroma, pgvector)
* Familiarity with cloud platforms such as AWS, Azure, or GCP
Preferred Skills
* Experience with AI observability and evaluation frameworks
* Exposure to guardrails, hallucination mitigation, and AI governance
* Knowledge of CI/CD and MLOps practices
* Experience working in enterprise or regulated environments