AI/ML Developer (Technology Specialist - Python / Agentic AI)

Argyllinfotech; Kansas City (MO); On-site; USD 140,000 - 210,000; Part time

Job summary

Argyllinfotech seeks an AI/ML Developer to design, build, and deploy production-ready, LLM-powered agents and workflows. You will craft multi-agent orchestration systems and advanced RAG pipelines, focusing on reliability and observability within a 6-month contract.

The role requires deep Python production experience, LLM engineering skills with LangChain or LangGraph, and strong backend design using FastAPI and PostgreSQL. On-site interview in Maryland Heights, MO.

Qualifications

• 8+ years of overall software development experience with deep Python in production environments.
• 2+ years building LLM applications, agents, and pipelines with LangChain/LangGraph.
• Experience with embeddings, vector search, re-ranking, context retrieval.
• Hands-on with OpenAI Chat Completions, function calls, streaming and JSON outputs.
• Proficiency in asynchronous Python (asyncio, FastAPI) and PostgreSQL with SQLAlchemy async/Alembic.
• Experience with Git, CI/CD pipelines, Docker, and Kubernetes basics.

Responsibilities

• Design, develop, and deploy production-ready, LLM-powered agents and workflows.
• Build advanced RAG pipelines with hybrid search, re-ranking, and retrieval strategies.
• Ensure high availability, observability, and reliability of backend services.

Skills

Python production

LLM engineering

RAG architecture

Asyncio

OpenAI API

PostgreSQL

Tools

LangChain

LangGraph

FastAPI

PostgreSQL

SQLAlchemy async

Alembic

Docker

Kubernetes

Job description

Job Title: AI/ML Developer (Technology Specialist - Python / Agentic AI) (Only USC and Green Cards)

Work Location: Maryland Heights, MO 63043 (Local candidates based in St. Louis willing to attend an in-person interview)

Contract Duration: 6 Months

Interview Process: In-person / Face-to-Face required

Position Overview

We are seeking a highly skilled AI/ML Developer to join our Agentic Platform Team on a 6-month contract basis. In this role, you will design, develop, and deploy production-ready, LLM-powered agents and workflows directly supporting field technicians. Working alongside the Platform Architect, you will play a key role in building resilient multi-agent orchestration systems and advanced RAG pipelines.

Key Responsibilities

• Agent Development & Orchestration: Design and deploy LLM-powered agents and multi-agent workflows using LangChain and LangGraph, implementing state management, conditional routing, and robust error handling.
• RAG & API Integration: Build advanced RAG pipelines utilizing hybrid search (semantic + keyword), re-ranking, and Reciprocal Rank Fusion. Integrate Azure OpenAI APIs with circuit breaker patterns, fallback logic, dynamic prompt management, and streaming support (WebSocket / SSE).
• Production Engineering & Reliability: Write clean, modular, and fully tested asynchronous Python code (FastAPI, asyncio) backed by PostgreSQL, ensuring high availability, system resilience, and proper LLM observability/tracing.

Required Qualifications

• Experience: 8 10+ years of overall software development experience with deep Python expertise in production environments.
• LLM Engineering: 2+ years of hands-on experience building LLM applications, agents, and pipelines using frameworks like LangGraph or LangChain.
• RAG Architecture: Solid experience with embeddings, vector search, re-ranking, and context retrieval strategies.
• LLM APIs & Prompting: Hands-on experience with OpenAI Chat Completions, function calling/tool execution, streaming, dynamic prompt management, and structured JSON output generation.
• Backend & System Design: Proficiency in asynchronous Python (asyncio, FastAPI), relational databases (PostgreSQL with SQLAlchemy async / Alembic), and microservice/distributed system architecture.
• DevOps & Testing: Standard experience with Git, CI/CD pipelines, Docker, and Kubernetes basics.

Preferred Qualifications

• Hands-on implementation of LangGraph StateGraph workflows (conditional edges, node pipelines, compiled graphs).
• Experience with multi-agent orchestration, routing, and RBAC-based access control.
• Familiarity with LLM observability platforms (e.g., Langfuse) for tracing latency and token metrics.
• Work with multi-modal AI systems (vision models and image analysis).
• Hands-on experience with vector databases (OpenSearch, Pinecone, pgvector) and AWS cloud services (Aurora PostgreSQL, EKS, IAM).
• Background in telecommunications or field service domain operations.