Staff Engineer

AI/ML Engineer – Virtual Relationship Manager (VRM) & Conversational Systems

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.

S​Ynechron’S Diversity & Inclusion Statement

Diversity & Inclusion are fundamental to our culture, and Synechron is proud to be an equal opportunity workplace and is an affirmative action employer. Our Diversity, Equity, and Inclusion (DEI) initiative ‘Same Difference’ is committed to fostering an inclusive culture – promoting equality, diversity and an environment that is respectful to all. We strongly believe that a diverse workforce helps build stronger, successful businesses as a global company. We encourage applicants from across diverse backgrounds, race, ethnicities, religion, age, marital status, gender, sexual orientations, or disabilities to apply. We empower our global workforce by offering flexible workplace arrangements, mentoring, internal mobility, learning and development programs, and more.

All employment decisions at Synechron are based on business needs, job requirements and individual qualifications, without regard to the applicant’s gender, gender identity, sexual orientation, race, ethnicity, disabled or veteran status, or any other characteristic protected by law.

Candidate Application Notice