For a hands-on learning experience to develop LLM applications, join our LLM Bootcamp today.
First 5 seats get a 30% discount! So hurry up!
Back to Careers

Software Engineer – Generative AI and LLMs

Remote | Pakistan

Full-Time | Pacific Time

About the product and job role:

Our Product: Ejento, built by Data Science Dojo, is a cutting-edge RAG platform that enables LLM application developers to build retrieval-augmented generation (RAG)-based applications efficiently. Our platform integrates advanced retrieval systems with LLMs to create scalable, context-aware AI solutions. We are dedicated to ensuring AI safety, reliability, and performance by developing robust LLM guardrails and evaluation frameworks.

Job Role: We are looking for Software Engineers specializing in Generative AI and LLMs to design and implement robust guardrails and evaluation frameworks for Ejento. This role is crucial in ensuring safe, reliable, and high-quality AI-generated outputs by integrating guardrails for security, compliance, and ethical considerations. The engineer will also develop an evaluation framework to measure model accuracy, robustness, and real-world performance across various use cases.

 

What you will do:

  • Design and optimize our platform to support the latest in LLMs, embeddings, tool use, and agentic patterns, keeping Ejento ahead of the curve.
  • Architect and refine multi-agent systems with tool use, memory, and coordination, turning AI into actual coworkers, not just chatbots.
  • Optimize semantic and hybrid search systems with techniques like RAG, grounding, and reranking to deliver precise, context-aware responses.
  • Develop clean, scalable APIs that let customers drop powerful AI into their apps with minimal lift and maximum impact.
  • Create rich, extensible integrations with platforms like Teams, Slack, SharePoint, Notion, and beyond, meeting users where they already work.
  • Use Ejento to build Ejento. You’ll test ideas in the wild, spot edge cases early, and ship with confidence.
  • Design with responsibility implements guardrails, safety filters, prompt injection protection, and access control from day one.
  • Read the latest arXiv papers before they trend, try open-source tools before they launch, and help us ship what others are still prototyping.
  • Partner with real users and customers to understand needs, unblock workflows, and deploy AI that makes their jobs easier, not harder. Design and implement LLM guardrails to prevent hallucinations, biases, and unsafe outputs within Ejento.

What we are looking for:

  • A degree in math, engineering or related disciplines. A degree in computer science and computer engineering may be helpful but not required. Some of our top engineers have degrees in math, industrial and mechanical engineering.
  • Understanding of Python programming, computer science fundamentals including OOP, algorithms, data structures.
  • Familiarity with LLM inference APIs (OpenAI, Hugging Face, Anthropic, etc.).
  • Experience developing APIs and integrating AI models into real-world applications
  • Deep interest in LLMs, multi-agent systems, and retrieval-augmented generation (RAG) techniques.
  • Knowledge of prompt engineering and expertise in leveraging AI tools for coding and automation.
  • Familiarity with AI development frameworks such as FastAPI, LangChain, or LlamaIndex, and agent frameworks like LangGraph or LlamaIndex Agents.
  • A strong ability to collaborate with cross-functional teams and translate business needs into AI-driven solutions.
  • A proactive, adaptable mindset with a passion for pushing AI technology forward.
  • Strong problem-solving skills, communication abilities, and the ability to work independently.

Nice to have skills:

  • Experience with designing large scale systems design and API
  • Experience with Docker, serverless architectures, and CI/CD deployment pipelines.
  • Familiarity with observability, monitoring, and logging tools like Sentry, Langfuse, Arize or similar.
  • Understanding of LLM guardrails, safety mechanisms, and responsible AI principles.
  • Hands-on experience with LLM frameworks like LangChain and LlamaIndex and similar.
  • Experience with tools for Agentic architectures like LangGraph, AutoGen and similar.
  • Experience with cloud platforms like Azure, AWS or GCP.

Apply Now

Apply Now
Training
Enterprise
Community
About
X-twitter
© Copyright – Data Science Dojo | Privacy Policy | Terms of Service