AI/ML Engineer

About the business

iGreenData -A Synechron company is a next-generation technology company focusing on Cloud, Data, and Digital first solutions that are changing how technology provides value to businesses, empowering organizations to take advantage of the scalability, reliability, and improved performance of cloud computing. We offer highly differentiated technology services to our customers. Our customers benefit from the industry-leading digital and cloud capabilities we deliver together with our niche partner ecosystem. We leverage our intellectual property and our unique family of accelerators to helping our customers develop and run Intelligent businesses and transform the customer experience.

What you'll contribute to the position

We're seeking a highly skilled AI/ML Engineer with expertise in building scalable, intelligent conversational systems and agent frameworks. The ideal candidate will have a strong background in containerized AI agents, semantic kernel development, observability, data management, API gateway deployment, and large language model (LLM) integrations to drive innovative VRM solutions.

Key Responsibilities:

• Develop and maintain containerized AI agents using frameworks like Langgraph, LangChain, and LangFuse.
• Implement semantic kernel solutions in Python for intelligent language processing.
• Design and optimize MCP tooling workflows without direct API calls, ensuring efficient tooling development.
• Define protocols for agent-to-agent (A2A) communication, ensuring reliable and scalable interactions.
• Implement observability solutions using Langfuse, Observe, and Obstacle for system monitoring and debugging.
• Integrate Retrieval-Augmented Generation (RAG) techniques leveraging DynamoDB, Bedrock, and embedding models for knowledge retrieval.
• Engineer context management and dialogue state tracking using Aurora DB.
• Build and deploy CI/CD pipelines for efficient agent deployment and updates, utilizing Docker, ECS Fargate, and FastAPI.
• Implement LLM as an arbitration or judgment system with ChatGPT-4 and OpenAI APIs.
• Manage container orchestration with ECS Fargate and Docker.
• Configure and optimize API Gateway layers with Kong Gateway for secure and scalable API management.
• Develop strategies to tackle agent scalability and performance challenges in large-scale environments.

Qualifications:

• Bachelor's or Master's degree in Computer Science, AI, Data Science, or related fields.
• Proven experience in building AI-powered agent systems with frameworks like LangChain, Langgraph, LangFuse.
• Strong Python development skills, especially in semantic kernel and NLP applications.
• Hands-on experience with DynamoDB, AWS Bedrock, embedding models, and RAG methodology.
• Deep knowledge of containerization (Docker), orchestration (ECS Fargate), and deployment pipelines (CI/CD).
• Familiarity with large language models (e.g., GPT-4, OpenAI API) as decision or judgment components.
• Experience with API management tools such as Kong Gateway.
• Expertise in system observability and monitoring (Langfuse, Observe, Obstacle).
• Knowledge of SQL/NoSQL databases, especially Aurora DB, for context and dialogue management.
• Strong problem-solving capabilities in scaling and optimizing agent architectures.
• Excellent communication and collaboration skills in a fast-paced environment.

Preferred Skills:

• Experience in protocol design for agent-to-agent communication.
• Familiarity with cloud infrastructure and serverless deployment models.
• Ability to implement secure, scalable, and maintainable AI solutions.

If this opportunity sound likes something you would be interested in, we want to hear from you Our team will assess your application, and if we feel that you could be a good fit for any of our client partners, we will be in touch regarding the next steps. You must have the right to live and work in this location to apply for this job.