Platform Engineer AI Workflows

We're looking for a Mid-Level Backend Developer to join our engineering team, working on backend systems that handle large-scale data and power AI agentic workflows. You'll design, build, and maintain server-side systems, APIs, and data pipelines, working closely with frontend, product, and DevOps teams to ship reliable, scalable software.

• Design, develop, and maintain backend services and RESTful/GraphQL APIs
• Build and manage systems that process, store, and query large-scale datasets efficiently
• Build and orchestrate AI agentic workflows — tool use, multi-step reasoning chains, agent-to-agent communication, and autonomous task execution
• Integrate LLM APIs (e.g., Anthropic Claude, OpenAI) into production backend systems
• Design, optimize, and maintain database schemas across PostgreSQL and MongoDB
• Implement and optimize search/indexing solutions, ideally using OpenSearch
• Write clean, well-tested, maintainable Python code using modern frameworks
• Optimize applications and data pipelines for performance, scalability, and reliability
• Collaborate with frontend engineers to integrate user-facing elements with server-side and agent logic
• Participate in code reviews and contribute to engineering best practices
• Debug and resolve production issues, including data pipeline failures and agent behavior edge cases
• Contribute to architecture and technical design discussions around data systems and agent orchestration

• 5-6 years of professional backend development experience
• Strong proficiency in Python, with hands-on experience in frameworks such as FastAPI, Django, or Flask
• Must have: solid working knowledge of PostgreSQL and MongoDB — schema design, indexing, query optimization, and performance tuning
• Demonstrated experience working with large-scale data — high-volume datasets, high-throughput systems, or data-intensive applications
• Practical experience building or integrating AI agentic systems (e.g., LangChain, LangGraph, LlamaIndex, CrewAI, or custom agent orchestration frameworks)
• Experience working with LLM APIs and prompt engineering for production use cases
• Solid understanding of API design, authentication, and security best practices
• Familiarity with version control (Git) and CI/CD workflows
• Experience with cloud platforms (mainly AWS)
• Strong problem-solving skills and attention to detail

• Hands-on experience with OpenSearch (or Elasticsearch) — indexing strategies, query DSL, cluster management, and performance tuning

• Experience with tool-calling/function-calling patterns and structured output generation from LLMs
• Familiarity with agent evaluation, observability, and monitoring tools
• Experience with data pipeline/streaming tools (Kafka, Airflow, Spark)
• Experience with containerization (Docker, Kubernetes)
• Exposure to caching systems (Redis, Memcached)
• Familiarity with Agile/Scrum methodologies
• Contributions to open-source AI/ML or agentic tooling projects