AI/BE (LLM‑focused)

About Us

Vee.com is a social impact SaaS startup committed to driving positive change. Our mission is to empower organizations with innovative solutions that make a difference. Join our collaborative and inclusive work culture where you can contribute to social impact while enjoying opportunities for professional growth and development. We’re building AI‑driven features into our platform to help clients deliver real social impact.

• Develop AI‑driven systems: Join a fast‑growing engineering team building a cutting‑edge, AI‑driven platform. You’ll own the end‑to‑end development of AI‑based services, from prototypes to reliable production deployments, while collaborating closely with product, customer success, and cross‑functional teams.
• Lead ML/AI initiatives: Design and implement backend systems that integrate seamlessly with large language models (LLMs). Create scalable inference pipelines and APIs to integrate generative AI into our core platform. Use prompt engineering and fine‑tuning techniques to ensure domain‑specific accuracy.
• Build a distributed, cloud‑native infrastructure: Work on a 100% cloud‑native, containerized distributed system designed for high availability. You’ll define architecture patterns and service boundaries, implement CI/CD pipelines, and contribute to system observability, resiliency, and scalability.
• Integrate LLMs and AI services: Implement Retrieval‑Augmented Generation (RAG) pipelines, agentic workflows, and vector search to provide context‑aware responses. Evaluate frameworks like LangChain, LangGraph, and LlamaIndex, and orchestrate multiple AI providers or models to optimize cost, latency, and reliability.
• Design APIs and backend services: Build robust APIs and microservices to support AI features, including real‑time chat or voice experiences. Manage the full lifecycle of backend - architecture, deployment, monitoring, and optimization for external AI dependencies.
• Develop evaluation & safety frameworks: Create robust prompt engineering systems and evaluation pipelines to measure model performance, reduce hallucinations, and ensure ethical and secure deployment. Implement AI safety measures and ensure compliance with regulations and privacy requirements.
• Continuous improvement: Stay up‑to‑date with emerging LLM models and tools. Research and implement the latest AI developments, evaluating trade‑offs between off‑the‑shelf APIs and custom models. Optimize model performance, latency, and inference cost through batching, caching, and model selection strategies.

• Backend and AI experience: 4+ years of hands‑on experience as a backend or AI engineer. Strong proficiency in Python and one other modern backend language (e.g., Go, Node.js, TypeScript) with experience building APIs and server‑side logic. Experience with FastAPI or similar frameworks is a plus.
• LLM & ML expertise: At least 2 years working with LLM‑based applications, including prompt tuning, RAG pipelines, and agentic workflows and agents. Practical experience integrating LLM APIs (OpenAI, Anthropic, Mistral, etc.) and using frameworks like LangChain and LangGraph.
• Distributed systems & cloud: Experience designing scalable backend systems and distributed architectures. Familiarity with containerization (Docker, Kubernetes) and cloud platforms (AWS, GCP, Azure) is required. Knowledge of caching, message queues, load balancing, and rate limiting for third‑party AI services is valued.
• Data pipelines and databases: Strong experience with SQL and NoSQL databases. Able to build data pipelines, manage vector databases, and integrate AI‑generated data into our systems. Familiarity with MLOps practices (CI/CD, monitoring, model versioning) is important.
• Evaluation & safety: Understanding of model evaluation frameworks, prompt engineering, and AI safety principles. Experience building eval pipelines and monitoring.
• Education: BS or MS in Computer Science, Math, or a related field, or equivalent engineering experience.

• Creative problem solver: You’re passionate about innovation and enjoy solving complex problems that deliver customer value. You balance speed and technical rigor, making informed trade‑offs between off‑the‑shelf APIs and custom model development.
• Self‑motivated & independent: Comfortable working independently in a dynamic startup environment. You have a backend‑first mindset and proactively explore new tools and frameworks, bringing them into our stack when appropriate.
• Team player & communicator: Strong collaboration and communication skills. Able to translate business requirements into technical solutions, mentor teammates, and explain AI concepts to non‑technical stakeholders.
• Commitment to continuous learning: Eager to stay abreast of the latest generative AI advancements, frameworks, and evaluation methods. You continually refine processes and share knowledge with the team.
• Passion for social impact: Excited about using technology to drive positive change. You’re enthusiastic about the mission to empower organizations and users through innovative, AI‑powered solutions.