ML/AI Engineer

Harnham; Dallas (TX); Hybrid; USD 146,000 - 166,000; Part time

Benefits offered by this job

Hybrid work model

Job summary

Harnham is partnering with an innovative technology company to build a next-generation agentic analytics platform. You will design, develop, and scale multi-agent AI workflows that transform natural language questions into reliable data insights, with emphasis on performance, observability, and cost efficiency.

The role focuses on hands-on engineering across LLMs, analytics, distributed systems, and software development, owning agent performance from design through deployment in a hybrid

Qualifications

• 5+ years of software engineering experience.
• 2+ years building production AI, ML, or LLM-powered applications.
• Experience with agent frameworks such as LangGraph, OpenAI Agent SDK, or similar.
• Hands-on experience with RAG, prompt engineering, tool/function calling, and agentic workflows.
• Experience with AI evaluation frameworks and observability tooling.
• Knowledge of vector databases and retrieval optimization.
• Strong SQL skills and experience with Snowflake, Databricks, or BigQuery.

Responsibilities

• Design and build multi-agent workflows using planning, routing, memory, and tool-calling architectures.
• Develop the tools that power agent decision-making, including SQL generation, data connectors, retrieval pipelines, and reporting capabilities.
• Build testing and evaluation systems to measure model and agent performance over time.
• Optimize AI systems for latency, cost, scalability, and reliability.
• Implement observability, tracing, and monitoring across agent workflows.
• Evaluate emerging AI tools and frameworks and make pragmatic technology decisions.

Skills

Software engineering

AI/ML production apps

LangGraph

OpenAI Agent SDK

Agent frameworks

RAG & prompts

Observability tools

Vector databases

SQL & data platforms

Tools

LangGraph

OpenAI Agent SDK

Job description

Harnham is partnering with an innovative technology company building a next-generation agentic analytics platform that uses AI agents to transform natural language questions into trusted, explainable business insights.

• Working Model: Hybrid
• Salary/Rate: $70 - $80 per hour W2
• Contract Type: 6 Month hybrid contract

The Role

As an ML/AI Engineer, you'll help build and scale a multi-agent AI platform that enables users to query data, run analysis, generate visualizations, and receive reliable, data-backed answers.

This is a hands-on engineering role focused on developing, orchestrating, and optimizing AI agents in production. You'll work at the intersection of LLMs, analytics, distributed systems, and software engineering, owning agent performance from design through deployment.

Key Responsibilities

• Design and build multi-agent workflows using planning, routing, memory, and tool-calling architectures.
• Develop the tools that power agent decision-making, including SQL generation, data connectors, retrieval pipelines, and reporting capabilities.
• Build testing and evaluation systems to measure model and agent performance over time.
• Optimize AI systems for latency, cost, scalability, and reliability.
• Implement observability, tracing, and monitoring across agent workflows.
• Evaluate emerging AI tools and frameworks and make pragmatic technology decisions.

Requirements

• 5+ years of software engineering experience.
• 2+ years building production AI, ML, or LLM-powered applications.
• Experience with agent frameworks such as LangGraph, OpenAI Agent SDK, or similar.
• Hands‑on experience with RAG, prompt engineering, tool/function calling, and agentic workflows.
• Experience with AI evaluation frameworks and observability tooling.
• Knowledge of vector databases and retrieval optimization.
• Strong SQL skills and experience working with modern data platforms such as Snowflake, Databricks, or BigQuery.