Role description
Role Summary
We are looking for a motivated AI Engineer with hands-on experience in Python and cloud platforms (AWS or Azure) to help design, build, and deploy Generative AI solutions.
This role will work closely with senior engineers, data teams, and business stakeholders to build AI-powered applications including LLM integrations, RAG pipelines, prompt workflows, and AI-driven automation solutions.
This is a hands-on engineering role, not research-only.
Key Responsibilities
- Build and integrate applications that leverage Large Language Models (LLMs).
- Develop Retrieval-Augmented Generation (RAG) pipelines.
- Implement prompt engineering techniques and structured output generation.
- Integrate AI services through APIs such as OpenAI, Azure OpenAI, or AWS Bedrock.
- Create AI-powered chatbots, assistants, and internal productivity tools that enhance business workflows.
- Write clean, scalable Python code that supports AI workflows.
- Develop REST APIs using frameworks such as FastAPI or Flask.
- Work with JSON, structured data, embeddings, and vector stores.
- Build data processing scripts that feed into AI pipelines.
Deploy AI applications using AWS services such as:
- S3
- Lambda
- Bedrock
- EC2
- API Gateway
Deploy AI applications using Azure services such as:
- Azure OpenAI
- Functions
- Blob Storage
- App Services
Support containerization using Docker.
Support CI/CD pipelines to ensure smooth and reliable cloud-based operations.
Work with structured and unstructured data sources.
Build connectors to databases such as:
- PostgreSQL
- MySQL
- SQL Server
Assist in creating vector databases using:
- FAISS
- Pinecone
- OpenSearch
Support model evaluation and logging.
Assist in monitoring, testing, and continuously improving AI systems.
Required Skills
8+ years of experience in software engineering or AI development.
Strong command of Python as the primary programming language.
Comfortable working with APIs and JSON-based integrations.
Foundational understanding of Large Language Models and Generative AI.
Familiarity with:
- Prompt Engineering
- Embeddings
- Vector Search
Hands-on experience with AWS or Azure.
Familiarity with Git and collaborative development workflows.
Preferred Qualifications
Experience with LangChain, LlamaIndex, or similar frameworks supporting Large Language Model applications.
Familiarity with Azure OpenAI or AWS Bedrock.
Practical experience with FastAPI for API development.
Basic understanding of:
- Retrieval-Augmented Generation (RAG) architecture
- AI model evaluation techniques
- MLOps fundamentals
Experience working with vector databases for embeddings and search functionality.
Exposure to Databricks.
Skills
About RCG Global Services
At Myridius, we transform the way businesses operate. Formerly known as RCG Global Services, our more than 50 years of expertise now drive a new vision—propelling organizations through the rapidly evolving landscapes of technology and business. We offer tailored solutions in AI, data analytics, digital engineering, and cloud innovation, addressing the unique challenges each industry faces. Our integration of cutting-edge technology with deep domain knowledge enables businesses to seize new opportunities, drive significant growth, and maintain a competitive edge in the global market. Our commitment is not just to meet expectations but to exceed them, ensuring measurable impact and fostering sustainable innovation. The success of Myridius is directly tied to the breakthroughs achieved by our clients. Together, we co-create solutions that not only solve today’s challenges but also anticipate future trends. At Myridius, we go beyond typical service delivery. We craft transformative outcomes that help businesses not just adapt, but thrive in a world of continuous change. Discover how Myridius can elevate your business to new heights of innovation. Visit us at www.myridius.com and start leading the change.
