Backend Lead - Python - Dallas at Photon

Job description

We are looking for a Backend Lead to architect and build the robust infrastructure required to power our Agentic AI products. You will lead the development of the "brain" of our platform—the layer where LLMs are transformed into autonomous agents that can plan, use tools, and solve complex problems. The ideal candidate is a Python expert who thrives on complex system design, concurrency, and the unique challenges of integrating probabilistic AI into deterministic backend environments. Key Responsibilities • Agent Architecture & Orchestration: Lead the design of multi-agent systems using frameworks like LangGraph, CrewAI, or AutoGen , ensuring agents can transition between states (Planning, Execution, Review) reliably. • Scalable API Development: Architect high-performance, asynchronous APIs (primarily using FastAPI ) to handle long-polling or streaming connections for AI-generated content. • Tooling & Function Calling Infrastructure: Build a secure "sandbox" environment that allows AI agents to execute code, query databases, and interact with third-party APIs safely and efficiently. • RAG & Memory Management: Oversee the integration of Vector Databases (e.g., Pinecone, Weaviate, or PGVector) and design "memory" systems that allow agents to retain context across sessions. • Observability & Tracing: Implement specialized monitoring and logging (using tools like LangSmith, Arize Phoenix, or OpenTelemetry ) to trace agent decision-making and debug "looping" behaviors. • Security & Guardrails: Design backend-level guardrails to prevent prompt injection and ensure that autonomous agents operate within strictly defined permission boundaries. • Leadership & Mentoring: Set the standard for Python coding excellence, conduct deep architectural reviews, and mentor engineers on the nuances of AI-integrated backend development. Technical Requirements • Python Mastery: 10+ years of professional backend experience, with expert-level knowledge of Asynchronous Programming (Asyncio) , Pydantic (v2), and Pytest. • AI Frameworks: Hands-on experience building production-grade applications with LangChain or similar orchestration libraries. • Concurrency & Task Management: Deep experience with message brokers and task queues (e.g., Redis, RabbitMQ, or Celery ) to manage long-running agentic tasks. • Database Expertise: Proficiency in PostgreSQL (relational) and at least one Vector Database . Experience in optimizing complex queries for AI retrieval. • Cloud Infrastructure: Strong knowledge of Docker, Kubernetes , and serverless architectures within AWS, Azure, or GCP. • Design Patterns: Mastery of microservices architecture, event-driven design, and API versioning. Preferred Qualifications • Experience with LLM fine-tuning or local model deployment (vLLM, Ollama). • Knowledge of Distributed Systems and handling the "cold start" or latency issues associated with large-scale AI models. • Background in Cybersecurity , specifically regarding autonomous systems and API security. Compensation, Benefits and Duration Minimum Compensation: USD 46,000 Maximum Compensation: USD 162,000 Compensation is based on actual experience and qualifications of the candidate. The above is a reasonable and a good faith estimate for the role. Medical, vision, and dental benefits, 401k retirement plan, variable pay/incentives, paid time off, and paid holidays are available for full time employees. This position is not available for independent contractors No applications will be considered if received more than 120 days after the date of this post Job Description Template

Requirements

Must-haves

The ideal candidate is a Python expert who thrives on complex system design, concurrency, and the unique challenges of integrating probabilistic AI into deterministic backend environments.
Agent Architecture & Orchestration: Lead the design of multi-agent systems using frameworks like LangGraph, CrewAI, or AutoGen , ensuring agents can transition between states (Planning, Execution, Review) reliably.
Scalable API Development: Architect high-performance, asynchronous APIs (primarily using FastAPI ) to handle long-polling or streaming connections for AI-generated content.
Tooling & Function Calling Infrastructure: Build a secure "sandbox" environment that allows AI agents to execute code, query databases, and interact with third-party APIs safely and efficiently.
RAG & Memory Management: Oversee the integration of Vector Databases (e.g., Pinecone, Weaviate, or PGVector) and design "memory" systems that allow agents to retain context across sessions.
Observability & Tracing: Implement specialized monitoring and logging (using tools like LangSmith, Arize Phoenix, or OpenTelemetry ) to trace agent decision-making and debug "looping" behaviors.
Security & Guardrails: Design backend-level guardrails to prevent prompt injection and ensure that autonomous agents operate within strictly defined permission boundaries.
Leadership & Mentoring: Set the standard for Python coding excellence, conduct deep architectural reviews, and mentor engineers on the nuances of AI-integrated backend development.
Technical Requirements
Python Mastery: 10+ years of professional backend experience, with expert-level knowledge of Asynchronous Programming (Asyncio) , Pydantic (v2), and Pytest.
AI Frameworks: Hands-on experience building production-grade applications with LangChain or similar orchestration libraries.
Concurrency & Task Management: Deep experience with message brokers and task queues (e.g., Redis, RabbitMQ, or Celery ) to manage long-running agentic tasks.
Database Expertise: Proficiency in PostgreSQL (relational) and at least one Vector Database . Experience in optimizing complex queries for AI retrieval.
Cloud Infrastructure: Strong knowledge of Docker, Kubernetes , and serverless architectures within AWS, Azure, or GCP.
Design Patterns: Mastery of microservices architecture, event-driven design, and API versioning.

Nice-to-haves

Experience with LLM fine-tuning or local model deployment (vLLM, Ollama).
Knowledge of Distributed Systems and handling the "cold start" or latency issues associated with large-scale AI models.
Background in Cybersecurity , specifically regarding autonomous systems and API security.
Compensation, Benefits and Duration
Maximum Compensation: USD 162,000
Compensation is based on actual experience and qualifications of the candidate. The above is a reasonable and a good faith estimate for the role.
This position is not available for independent contractors
No applications will be considered if received more than 120 days after the date of this post
Job Description Template

Application prep

Use the role’s language and application details while tailoring your materials.

Keywords to mirror

aipythonapidockerkubernetesawsazuregcpllm

Platform: oracle-cloud
Effort: medium

Benefits

Benefits detected in the listing.

Dental

Vision

401k

Paid Time Off