Artificial Intelligence Engineer

Company Description

ProHance is a fast-growing B2B SaaS company focused on helping enterprises gain a clear, data-driven view of workforce productivity and operational effectiveness. Trusted by global enterprises across industries, ProHance enables leaders to make better decisions by combining deep work analytics with actionable insights.

As enterprises rapidly adopt AI and automation, ProHance is at the forefront of this shift — building AI-powered, insight-driven products that help organizations measure impact, improve productivity, and realize ROI from technology investments. Central to this vision is the concept of eGDP: the idea that productive hours, work output, AI usage, and vendor effort can be converted into a single, defensible measure of enterprise economic activity.

We are now building the AI layer of the ProHance platform — including the intelligence engine, the ProHance Agent, and the measurement framework for human + AI productivity governance. These roles are foundational to that mission.

Role Description

We are looking for an AI Systems Engineer to design, build, and ship the ProHance Agent and the agentic AI infrastructure that powers our AI-first productivity governance platform. This role goes well beyond prompt engineering. You will architect multi-step reasoning workflows, design the retrieval and grounding systems that give our AI accurate context over enterprise workforce data, build the evaluation harnesses that ensure our AI is reliable and trustworthy at scale, and own the LLM operations layer that keeps production AI systems healthy. Just as importantly, you will help define how AI-native software gets built. Engineering an AI system is a different discipline from traditional software — behaviour is specified, generated, evaluated, and refined rather than deterministically coded. We want someone who will experiment with, and codify, new SDLC paradigms for this world: generator–evaluator loops, evaluation-driven development, intent expression, and loop engineering as first-class practices.

The ProHance Agent is a strategically important product initiative. It needs to reason over complex, heterogeneous workforce telemetry, surface actionable insights to operations and finance leaders, and operate with the transparency and governance standards that regulated enterprise environments demand. You will be the person who makes that real — from architecture to production.

Key Responsibilities

ProHance Agent Architecture & Development

Lead the design and development of the ProHance Agent — an AI system capable of reasoning over workforce telemetry, benchmarking data, and workflow signals to surface insights and recommendations for enterprise operations leaders

Prompt Architecture & Context Engineering

Design and maintain the prompt architecture for ProHance AI features — system prompts, task prompts, tool-calling schemas, and structured output specifications across multiple LLM providers (e.g., OpenAI GPT, Anthropic Claude, Google Gemini)

RAG, Retrieval & Knowledge Architecture

Design and implement Retrieval-Augmented Generation (RAG) systems that allow ProHance AI to reason accurately over enterprise-scale workforce data, benchmarks, process definitions, and historical patterns

Evaluation, Quality & LLM Operations

Build and maintain evaluation harnesses — golden datasets, automated eval pipelines, and regression suites — to measure AI output quality across hallucination, groundedness, relevance, and reasoning accuracy

AI-Native SDLC & Loop Engineering

Pioneer new engineering paradigms for the AI era — treating AI system development as a discipline where behaviour is specified, generated, evaluated, and refined, rather than deterministically coded

Production Deployment & Platform Integration

Integrate AI agents cleanly into the ProHance platform via APIs and function calling, with appropriate security, access controls, and privacy handling for enterprise workforce data

Required Qualifications

• Experience: 2–4 years in software engineering or AI product development, with at least 2 years of hands-on production LLM application development
• Agentic systems: Demonstrable experience designing and shipping agentic or multi-step AI systems — not just single-turn prompt-response applications
• LLM frameworks: Strong proficiency with LangChain, LangGraph, LlamaIndex, CrewAI, AutoGen, or equivalent orchestration frameworks; ability to go beyond framework defaults when needed
• LLM providers: Hands-on experience building against modern LLMs such as OpenAI GPT, Anthropic Claude, or Google Gemini
• RAG and retrieval: Hands-on experience with RAG architecture, vector databases, embedding pipelines, and retrieval quality optimisation
• Evaluation discipline: Experience building eval harnesses, golden datasets, and automated quality pipelines — not just manual spot-checking
• Programming: Expert-level Python for API orchestration, data processing, and AI pipeline development; working proficiency in TypeScript is a plus for tooling and integration layers
• Infrastructure: Working knowledge of cloud platforms (AWS, Azure, or GCP), containerisation and orchestration (Docker, Kubernetes), CI/CD pipelines, and Git
• Production mindset: Track record of shipping AI systems that work reliably in production — not just demos or prototypes
• Experimentation mindset: Demonstrated curiosity and rigour in exploring emerging AI engineering paradigms — generator–evaluator loops, evaluation-driven development, and AI-native SDLC practices Preferred Qualifications
• Experience with enterprise-grade AI governance requirements — auditability, explainability, access control, and data privacy in regulated environments
• Familiarity with workforce analytics, operational telemetry, or time-series data as a retrieval and reasoning domain
• Understanding of model routing, fine-tuning (LoRA, QLoRA), and inference optimisation
• Experience with distributed systems and microservices architecture
• Experience with multi-modal reasoning or structured data (tables, metrics) as first-class context for LLMs
• Contributions to open-source LLM tooling, published research on LLM evaluation, or demonstrated thought leadership in AI systems engineering — including new approaches to building AI-native software