Senior Software Engineer - AI

About the role

Newfold Digital is seeking a Senior Software Engineer to help build the agent‑powered backbone of its AI platform. You will design, develop, and scale high‑performance APIs and multi‑agent workflows that serve millions of users worldwide.

Key responsibilities

• Design and scale async REST/WebSocket APIs using Python 3.11+ and FastAPI with clean vertical‑slice architecture.
• Implement multi‑agent workflows with Semantic Kernel, handling handoff, sequential and concurrent routing.
• Integrate LLM providers (OpenAI GPT‑4.1/mini, Google Gemini 2.5 Flash) behind a provider‑agnostic layer for A/B testing and cost‑aware routing.
• Deliver Retrieval‑Augmented Generation using Azure AI Search, pgvector or Chroma.
• Expose tool‑using agents via OpenAI Assistants for data‑analysis and file‑manipulation tasks.
• Evolve database schemas with SQLModel/SQLAlchemy 2 and Alembic; optimise PostgreSQL for high‑concurrency async access.
• Maintain CI/CD pipelines (Bitbucket, Jenkins) that lint, type‑check, test, containerise (Docker) and deploy.
• Instrument services with structlog JSON logs, OpenTelemetry traces and cost/latency metrics.

Required profile

• 5+ years building production APIs in Python; 2+ years with FastAPI or similar async stack.
• Deep knowledge of async I/O, Pydantic v2, dependency injection and observability.
• Hands‑on experience with Semantic Kernel or comparable agent frameworks.
• Practical RAG implementations using Azure AI Search, pgvector or Chroma.
• Strong PostgreSQL expertise, including SQLModel/SQLAlchemy 2 and Alembic migrations.
• Proven integrations with LLM APIs (OpenAI, Gemini) and structured‑output design.
• Experience with Poetry for dependency management and end‑to‑end CI/CD ownership.
• Excellent analytical and problem‑solving abilities; remote‑work readiness with daily overlap 09:00‑13:00 EST.

Required skills

• Python 3.11+
• FastAPI
• Async I/O
• Pydantic v2
• Dependency Injection
• Semantic Kernel
• OpenAI GPT‑4.1 / Google Gemini
• Azure AI Search
• pgvector / Chroma
• SQLModel
• SQLAlchemy 2
• Alembic
• PostgreSQL
• Poetry
• Docker
• Bitbucket
• Jenkins
• structlog
• OpenTelemetry
• GitHub Copilot
• Cursor