Job Description
Duties
Position Description
We are seeking an innovative AI/ML Engineer with 3-5 years of experience to build and operationalize autonomous AI systems that solve complex business problems. This role requires expertise in Python development, the LangChain framework, and core AWS services to develop scalable, production-ready and secure AI agents integrated with enterprise systems using protocols like the Model Context Protocol (MCP). The ideal candidate will transform prototypes into robust, secure, and observable solutions.
Key Responsibilities
Design & Development: Architect and develop end-to-end agentic AI systems and multi-agent workflows capable of planning, reasoning, and tool use.
AWS Integration:Leverage AWS services such as Amazon Bedrock (Agent Core, Knowledge Bases), Amazon SageMaker, AWS Lambda, Amazon DynamoDB, and Amazon S3 for scalable and secure deployment.
Framework Implementation:Build and maintain RAG (Retrieval-Augmented Generation) pipelines and agentic workflows using frameworks like LangChain or LangGraph.
Protocol & API Development:Implement and manage Model Context Protocol (MCP) connections for standardized tool calling and data exchange between agents and internal systems.
Prompt Engineering & Optimization:Apply advanced prompt engineering techniques, including Chain-of-Thought and ReAct patterns, to improve agent performance, reduce latency, and optimize token usage.
MLOps & Deployment: Define and manage CI/CD pipelines, containerization (Docker/Kubernetes), and monitoring/logging with tools like Amazon CloudWatch to ensure reliability and governance of AI solutions.
Collaboration:Partner with data engineers, product managers, and security teams to translate business requirements into technical solutions and ensure compliance with responsible AI practices.
Required Qualifications & Skills
Strong proficiency in Python and experience with building RESTful services using frameworks like FastAPI.
Hands-on experience with AWS AI services, particularly Amazon Bedrock and Amazon SageMaker.
Proven experience in designing and deploying agentic AI systems in a production environment.
Experience with generative AI frameworks such as LangChain or LangGraph.
Familiarity with the Model Context Protocol (MCP) specifications and Agent-to-Agent (A2A) communication protocols.
Knowledge of vector databases (e.g., Pinecone, Opensearch) for memory and knowledge management in RAG systems.
Strong understanding of MLOps practices, CI/CD, and cloud infrastructure management.
Excellent problem-solving skills and the ability to articulate complex technical concepts to non-technical audiences.
Skills
Minimum of 3 years of experience with strong programming skills in languages such as Python, R, or Java. In-depth knowledge of machine learning algorithms, techniques, and frameworks (e.g., TensorFlow, PyTorch, scikit-learn). Proficiency in data preprocessing, feature engineering, and model evaluation. Experience with big data processing tools and frameworks (e.g., Hadoop, Spark) is a plus. Solid understanding of statistical analysis and experimental design. Familiarity with cloud platforms (e.g., AWS, GCP) and distributed computing. Strong problem-solving skills and the ability to work on complex, open-ended problems. Excellent communication and collaboration skills to work effectively in cross-functional teams. Attention to detail and the ability to manage multiple projects simultaneously.
Education
Bachelor's degree in Computer Science, Mathematics, Statistics, or a related field. Master's or Ph.D. in a relevant field is preferred.
