Senior AI Platform Engineer

Overview

About Intelmatix

Job Summary

Platform Development

• Design, develop, and maintain the core platform services that power EDIX
• Implement foundational platform components: API gateways, service orchestration, configuration management
• Build shared infrastructure: dynamic configuration, service discovery, inter-service communication

AI Infrastructure & Stores

• Design abstraction layers (factory patterns) for vector stores, LLMs, and other AI components
• Support multiple backend implementations (OpenSearch, Pinecone, pgvector)
• Build and optimize retrieval pipelines across vector databases, graph databases, and embedding stores
• Implement agentic frameworks and orchestration patterns (LangGraph, LangChain, or similar)
• Support multiple LLM providers (AWS Bedrock, OpenAI, Anthropic) through unified interfaces
• Build data pipelines for document and media processing (ingestion, chunking, embedding, indexing)

Platform APIs & Services

• Develop and maintain highly-available API endpoints (RESTful, async patterns)
• Serve platform capabilities to both internal teams and client-facing products
• Implement error handling, retry logic, caching strategies, and fallback patterns
• Optimize latency and throughput for both traditional and AI inference workloads
• Design APIs with extensibility and multi-tenancy in mind

Quality & Standards

• Write clean, well-tested, documented code with comprehensive unit and integration tests
• Participate in code reviews and contribute to technical documentation and runbooks
• Establish and enforce engineering standards for the platform codebase

Collaboration

• Coordinate with DevOps on deployment, scaling, and infrastructure optimization
• Collaborate with Data Science and ML teams to productionize models as platform services

Education

Experience

Technical Skills

• Strong proficiency in Python; additional experience in Java, Go, or TypeScript is a plus
• Strong understanding of system design, platform architecture, distributed systems, and data modeling
• Strong API development skills (REST, async patterns, WebSockets) and experience designing platform APIs consumed by multiple teams
• Experience with cloud platforms and infrastructure — AWS preferred (Lambda, SQS, OpenSearch, RDS, Bedrock, S3)
• Experience with agentic frameworks (LangChain, LangGraph, CrewAI, or similar) and orchestration patterns
• Experience with containerization (Docker) and orchestration (Kubernetes, ECS) including deployment, scaling, and event-driven patterns
• Experience with Infrastructure-as-Code (IaC) tools like Terraform, CloudFormation.
• Experience with CI/CD pipelines (GitHub Actions, Jenkins, AWS CodePipeline)
• Experience with using LLM APIs and providers (AWS Bedrock, OpenAI, Anthropic, or similar)
• Experience with vector databases and embedding stores (OpenSearch, Pinecone, pgvector, or similar)
• Experience with monitoring and observability tools (Prometheus, Grafana, DataDog, CloudWatch) — including AI-specific metrics (latency, token usage, quality)
• Familiarity with prompt engineering, evaluation frameworks.
• Familiarity with MCP (Model Context Protocol), A2A (Agent to Agent Protocol) and tool-use patterns

Soft Skills

• Excellent communication skills, adaptable, self-motivated, and capable of thriving in a fast-paced, unstructured startup environment
• Platform mindset — you think about reusability, extensibility, and how other teams will consume what you build
• Strong ownership mentality — you ship production systems, not experiments
• Nice to Have
• Experience building scalable, multi-tenant platform systems consumed by multiple product teams
• Experience with RAG (Retrieval-Augmented Generation) architectures and optimization techniques
• Exposure to both NoSQL and SQL database technologies (DynamoDB, MongoDB, PostgreSQL, AWS Aurora, OpenSearch)
• Experience with API gateway and service mesh patterns (Kong, Envoy, AWS API Gateway)
• Familiarity with modern authentication schemes such as OAuth, JWTs, or cookies
• Exposure to graph databases (Neo4j, Amazon Neptune) and knowledge graph construction
• Experience working in fast-paced startup environments, contributing to rapid development and delivery-driven projects
• Proven ability to thrive and adapt during significant company growth