Architect and maintain Python-based services using FastAPI for internal and customer-facing AI use cases
Build and scale secure, well-structured API endpoints that interface with LLMs, vector stores, and agentic tools
Implement orchestration logic and tool chaining for advanced agent workflows
Optimize service performance and latency across AI infrastructure layers
Collaborate with frontend, AI, and devops teams to ensure system-wide reliability and observability
Set up robust test coverage and CI pipelines for backend services
Contribute to our modular architecture for tool-based reasoning agents
Stay current with emerging trends in AI engineering, LLM integrations, and scalable backend systems

Requirements

3+ years of experience as a full-stack engineer, building scalable backend systems in Python
Strong knowledge of Flask for building and scaling product grade APIs
Experience with LLM orchestration frameworks (e.g., LiteLLM) and integrating OpenAI or similar
Familiarity with vector databases, embeddings, and RAG patterns
Experience building and maintaining infrastructure that integrates with frontends, CLIs, and external APIs
Comfortable with GitHub, Docker, and CI/CD tooling (e.g., GitHub Actions)
Proficiency in writing robust, tested, and well-documented backend code

Benefits

Applicant Tracking System Keywords

Tip: use these terms in your resume and cover letter to boost ATS matches.

Hard Skills & Tools

PythonFastAPIFlaskLLM orchestration frameworksOpenAIvector databasesembeddingsRAG patternsCI/CDbackend code

Soft Skills

collaborationcommunicationproblem-solvingreliabilityobservability