harri is the frontline employee experience platform built for companies who have service at the heart of their business. The solution is built on the notion that the customer experience will never exceed the employee experience. The Harri suite of talent attraction, workforce management and employee engagement technologies enable organizations to attract, manage, engage and retain the best talent for their business.

Hospitality is in our DNA, with most of our global team having front line and management restaurant experience - we are changing the landscape of our industry and frontline workers technology. We need the very best and brightest to join us on this mission to disrupt the market as it stands today. 

Based in NYC, Harri has global offices in the UK, Palestine and India and has been awarded: Top 50 Startup by LinkedIn, Best Enterprise Solution for HR/Workforce by HR Tech Awards & NYC Best Tech Startup for the Tech in Motion Events Timmy Awards.

Job Summary:

We are looking for a motivated and curious Generative AI Engineer (Junior to Mid-Level) to join our growing Generative AI team at Harri. In this role, you’ll work closely with senior engineers to help develop and deploy cutting-edge generative AI systems across real business use cases. You'll contribute to solutions that integrate large language models (LLMs), embeddings, vector databases, and GenAI development frameworks. This is a hands-on role that offers the opportunity to work with production-grade GenAI technologies, grow your skill set, and have a real impact on user-facing AI features.

Role and Responsibilities 

Typical duties and responsibilities for Gen-AI engineer position may include but not limited to: 

• Support the fine-tuning, deployment, and integration of large language models (LLMs) and other generative models (e.g., GPT, Mistral).

• Build and maintain retrieval-augmented generation (RAG) pipelines using embeddings and vector databases like FAISS, Pinecone, or Chroma.

• Contribute to prompt engineering, schema design, and function calling logic to guide LLM behavior in production workflows.

• Work with GenAI development frameworks to build, orchestrate, route, and serve GenAI-powered features, workflows, and agents.

• Stay up to date with the latest advancements in generative AI, prompt tooling, and language model APIs.

• Participate in experiments exploring new architectures, model capabilities, and prompting techniques.

• Help evaluate model behaviors and document findings to support continual improvement.

• Work under the guidance of senior AI engineers and participate in code reviews, design discussions, and technical planning.

• Take ownership of well-scoped components and contribute to production releases.

• Embrace a learning-first environment and help foster a collaborative, transparent team culture.

• Collaborate with cross-functional teams (engineering, product, design) to deliver user-facing GenAI features.

• Implement backend APIs and services powered by LLMs, including local and cloud-hosted models.

• Support LLM observability efforts to track pipelines’ execution, logs, LLM calls, performance, latency, and failure cases.

• Assist in evaluating and mitigating bias, hallucination, and safety risks in generative AI systems.

• Ensure that outputs and user-facing AI behavior follow responsible AI principles and privacy standards.

• Knowledge sharing and culture building as we work in team structure, it is very essential to have the spirit of sharing the knowledge.

• Keep aligned with HARRI’s team(s) coding and design standards.

• Ability to communicate and work well with others.

• Ability to deliver on time keeping a high quality of work.

• To quickly become an expert in our tech stack, specifically the systems relating to your role. Requesting training when required.

• Check in with your line manager and update on your progress.

• To live and breathe the Harri Company values.

harri is the frontline employee experience platform built for companies who have service at the heart of their business. The solution is built on the notion that the customer experience will never exceed the employee experience. The Harri suite of talent attraction, workforce management and employee engagement technologies enable organizations to attract, manage, engage and retain the best talent for their business.

Hospitality is in our DNA, with most of our global team having front line and management restaurant experience - we are changing the landscape of our industry and frontline workers technology. We need the very best and brightest to join us on this mission to disrupt the market as it stands today. 

Based in NYC, Harri has global offices in the UK, Palestine and India and has been awarded: Top 50 Startup by LinkedIn, Best Enterprise Solution for HR/Workforce by HR Tech Awards & NYC Best Tech Startup for the Tech in Motion Events Timmy Awards.

Job Summary:

We are looking for a motivated and curious Generative AI Engineer (Junior to Mid-Level) to join our growing Generative AI team at Harri. In this role, you’ll work closely with senior engineers to help develop and deploy cutting-edge generative AI systems across real business use cases. You'll contribute to solutions that integrate large language models (LLMs), embeddings, vector databases, and GenAI development frameworks. This is a hands-on role that offers the opportunity to work with production-grade GenAI technologies, grow your skill set, and have a real impact on user-facing AI features.

Role and Responsibilities 

Typical duties and responsibilities for Gen-AI engineer position may include but not limited to: 

• Support the fine-tuning, deployment, and integration of large language models (LLMs) and other generative models (e.g., GPT, Mistral).

• Build and maintain retrieval-augmented generation (RAG) pipelines using embeddings and vector databases like FAISS, Pinecone, or Chroma.

• Contribute to prompt engineering, schema design, and function calling logic to guide LLM behavior in production workflows.

• Work with GenAI development frameworks to build, orchestrate, route, and serve GenAI-powered features, workflows, and agents.

• Stay up to date with the latest advancements in generative AI, prompt tooling, and language model APIs.

• Participate in experiments exploring new architectures, model capabilities, and prompting techniques.

• Help evaluate model behaviors and document findings to support continual improvement.

• Work under the guidance of senior AI engineers and participate in code reviews, design discussions, and technical planning.

• Take ownership of well-scoped components and contribute to production releases.

• Embrace a learning-first environment and help foster a collaborative, transparent team culture.

• Collaborate with cross-functional teams (engineering, product, design) to deliver user-facing GenAI features.

• Implement backend APIs and services powered by LLMs, including local and cloud-hosted models.

• Support LLM observability efforts to track pipelines’ execution, logs, LLM calls, performance, latency, and failure cases.

• Assist in evaluating and mitigating bias, hallucination, and safety risks in generative AI systems.

• Ensure that outputs and user-facing AI behavior follow responsible AI principles and privacy standards.

• Knowledge sharing and culture building as we work in team structure, it is very essential to have the spirit of sharing the knowledge.

• Keep aligned with HARRI’s team(s) coding and design standards.

• Ability to communicate and work well with others.

• Ability to deliver on time keeping a high quality of work.

• To quickly become an expert in our tech stack, specifically the systems relating to your role. Requesting training when required.

• Check in with your line manager and update on your progress.

• To live and breathe the Harri Company values.