Senior AI Platform Engineer

About Intelmatix

Intelmatix is a cutting-edge deep tech company specializing in Artificial Intelligence (AI), established in July 2021 by a team of MIT scientists. Our mission is to empower enterprises to evolve into cognitive organizations—businesses that leverage AI and Decision Intelligence to drive smarter, more accurate, and outcome-focused decisions. By integrating advanced AI capabilities, we help organizations enhance operational efficiency, reduce errors, and achieve superior business results across all functional areas.

Job Overview

We are seeking a highly skilled and motivated Senior AI Platform Engineer to join our dynamic Platform team. In this pivotal role, you will be responsible for designing, developing, and maintaining the foundational infrastructure that powers EDIX, our flagship enterprise Decision Intelligence product. Your work will span core platform services, API layers, and advanced AI-driven capabilities, including agentic frameworks, retrieval pipelines, and LLM orchestration. This is a hands-on engineering position where you will own and evolve the systems that ensure EDIX operates seamlessly, efficiently, and at scale.

Key Responsibilities

Platform Development

• Design, develop, and maintain the core platform services that underpin EDIX, ensuring scalability, reliability, and performance.
• Implement foundational platform components such as API gateways, service orchestration, and configuration management to support robust system operations.
• Build shared infrastructure components, including dynamic configuration systems, service discovery mechanisms, and efficient inter-service communication protocols.

AI Infrastructure & Data Management

• Design and implement abstraction layers (e.g., factory patterns) for vector stores, LLMs, and other AI components to ensure flexibility and maintainability.
• Support and integrate multiple backend implementations, including vector databases (OpenSearch, Pinecone, pgvector), graph databases, and embedding stores.
• Develop and optimize retrieval pipelines that seamlessly integrate vector databases, graph databases, and embedding stores to enhance AI-driven decision-making.
• Implement agentic frameworks and orchestration patterns using tools such as LangGraph, LangChain, or similar technologies to enable advanced AI workflows.
• Support multiple LLM providers (e.g., AWS Bedrock, OpenAI, Anthropic) through unified interfaces, ensuring seamless integration and scalability.
• Build and maintain robust data pipelines for document and media processing, including ingestion, chunking, embedding, and indexing to support AI-driven applications.

Platform APIs & Services

• Develop and maintain highly available API endpoints using RESTful and asynchronous patterns to serve both internal teams and client-facing products.
• Implement advanced error handling, retry logic, caching strategies, and fallback mechanisms to ensure system resilience and performance.
• Optimize latency and throughput for both traditional and AI inference workloads to deliver a seamless user experience.
• Design APIs with extensibility and multi-tenancy in mind, ensuring they can scale to meet the evolving needs of diverse enterprise clients.

Quality Assurance & Collaboration

• Write clean, well-tested, and thoroughly documented code, accompanied by comprehensive unit and integration tests to maintain high standards of reliability.
• Participate actively in code reviews and contribute to the development of technical documentation and operational runbooks.
• Establish and enforce engineering standards for the platform codebase to ensure consistency, security, and maintainability.
• Collaborate closely with DevOps teams to optimize deployment strategies, scaling solutions, and infrastructure performance.
• Work alongside Data Science and ML teams to productionize models as scalable platform services, bridging the gap between research and operational excellence.

Qualifications & Skills

Education & Experience

• Bachelor's or Master's degree in Computer Science, Engineering, or a related technical field, or equivalent professional experience.
• Minimum of 6 years of professional software engineering experience, with at least 3 years dedicated to platform development and the creation of platform-wide solutions.
• At least 1 year of hands-on experience working with AI/Generative AI systems in production environments.

Technical Proficiency

• Strong proficiency in Python; additional experience in Java, Go, or TypeScript is considered a valuable asset.
• Deep understanding of system design, platform architecture, distributed systems, and data modeling principles.
• Expertise in API development, including RESTful services, asynchronous patterns, and WebSockets, with a focus on designing platform APIs consumed by multiple teams.
• Comprehensive experience with cloud platforms and infrastructure, with a preference for AWS (e.g., Lambda, SQS, OpenSearch, RDS, Bedrock, S3) and familiarity with GCP.
• Proficiency in containerization technologies (e.g., Docker, Kubernetes) and CI/CD pipelines to ensure efficient and reliable deployments.
• Experience with monitoring, logging, and observability tools to maintain system health and performance.

If you are a passionate platform engineer with a proven track record of building and scaling AI-powered systems in production, we invite you to apply and contribute to Intelmatix's mission of transforming enterprises into cognitive organizations.