Senior GenAI Engineer

Position Overview

Merci Technologies is seeking an experienced Senior Generative AI Engineer to design, develop, and deploy enterprise-grade AI solutions leveraging Large Language Models (LLMs), Retrieval-Augmented Generation (RAG), agentic workflows, and modern AI platforms.

Location
:
Offshore (Remote)
Employment
Type
:
Contract / Contract-to-Hire / Full-Time
Client
:
Confidential (Through Merci Technologies)

The ideal candidate will have strong experience building production-ready AI applications using OpenAI, Azure OpenAI, Anthropic, Lang Chain, vector databases, and cloud-native technologies. This role requires hands-on engineering expertise as well as the ability to collaborate with business stakeholders, data teams, and solution architects.

• Design and develop Generative AI solutions for enterprise clients.
• Build and optimize RAG pipelines using vector databases and semantic search.
• Develop AI-powered chatbots, copilots, and knowledge management solutions.
• Integrate LLMs with enterprise applications, APIs, and data sources.
• Engineer prompt frameworks for accuracy, reliability, and performance.
• Implement evaluation and monitoring mechanisms for AI applications.
• Create scalable APIs and microservices supporting AI workloads.
• Collaborate with data engineers and cloud architects to deploy AI solutions.
• Ensure security, compliance, and responsible AI practices.
• Document technical designs, architecture decisions, and development standards.

• Bachelor's degree in Computer Science, Engineering, Data Science, or a related field.
• Master's degree preferred.

• 5+ years of software engineering experience.
• 2+ years of hands-on Generative AI development.
• Experience deploying AI solutions in production environments.
• Strong understanding of machine learning concepts and LLM architectures.

• Python
• FastAPI or Flask
• Lang Chain or Lang Graph
• OpenAI API
• Azure OpenAI
• Prompt Engineering
• Vector Databases (Pinecone, Weaviate, Chroma, Qdrant, or Milvus)
• REST APIs
• Git
• Docker

• Anthropic Claude
• Google Gemini
• Hugging Face
• Semantic Kernel
• Kubernetes
• Azure AI Foundry
• AWS Bedrock
• MLOps
• CI/CD Pipelines

• Microsoft Azure AI Engineer Associate
• Microsoft Azure Solutions Architect Expert
• AWS Machine Learning Specialty
• Databricks Generative AI Certification

• Excellent communication skills.
• Ability to translate business requirements into technical solutions.
• Strong analytical and problem-solving skills.
• Ability to work effectively in a remote, distributed team environment.
• Self-starter with strong ownership mentality.

Within the first 90 days, the successful candidate will:

• Deliver at least one production-ready AI solution.
• Build scalable RAG-based applications.
• Improve LLM response quality through advanced prompting techniques.
• Contribute to reusable AI frameworks and accelerators.
• Support client-facing AI initiatives and proofs of concept.