Generative Ai

Company: AI Workfllow
Location: Remote (Open to applicants worldwide)
Experience: 3+ years in Generative AI / LLM development
Employment Type: Full-time, Remote

About AI Workfllow

AI Workfllow is a cutting-edge AI automation company building advanced AI agents and Agentic AI systems for businesses worldwide. From voice call agents to custom task-specific agents, our solutions automate workflows, improve productivity, and drive ROI for clients across industries including eCommerce, Legal, Finance, Insurance, and Marketing.

Our global clients include BVL Marketing Inc., Trilegal, CLXNS, Jyote, Moneyloji, and Build.com. We’re backed by a powerful combination of deep domain expertise, modern AI stacks, and real-world impact.

Role Overview

We’re looking for a skilled Generative AI Engineer who thrives at the intersection of language models, engineering, and intelligent task automation. You’ll play a key role in building next-gen AI agents using tools like OpenAI, Claude, Gemini, Llama, and Retrieval-Augmented Generation (RAG).

You’ll work alongside a globally distributed team of product thinkers, designers, and developers to create AI systems that don’t just respond — they reason, take action, and create value.

Key Responsibilities

• Build and fine-tune generative AI agents using LLMs like GPT-4, Claude, Llama, etc.
• Integrate LLMs with proprietary tools and APIs to enable autonomous decision-making agents.
• Implement Retrieval-Augmented Generation (RAG) pipelines and document parsing.
• Design workflows and prompts that enable AI agents to follow complex task flows.
• Experiment with tools like LangChain, Haystack, Semantic Kernel, and OpenAgent frameworks.
• Translate product requirements into scalable, production-ready AI systems.
• Collaborate with frontend/backend teams to deploy agents across platforms.
• Monitor and evaluate agent behavior and improve reliability through fine-tuning and prompt engineering.

Required Skills & Experience

• 3+ years of hands-on experience in generative AI, LLMs, or NLP
• Strong proficiency with Python and AI libraries such as LangChain, Transformers, PyTorch, or HuggingFace
• Experience building end-to-end applications using LLM APIs (OpenAI, Anthropic, etc.)
• Exposure to RAG-based workflows, embeddings, and vector databases (e.g., Pinecone, Weaviate, FAISS)
• Understanding of prompt engineering, few-shot learning, and multi-agent workflows
• Familiarity with REST APIs and integrating third-party tools into AI workflows
• Experience deploying scalable models to production using Docker/GCP/AWS

Nice to Have

• Prior work on AI agents or autonomous task execution systems
• Contributions to open-source GenAI projects
• Experience with speech-to-text or AI voice agents (Whisper, Vapi, etc.)
• Background in UX for conversational interfaces

Perks & Benefits

• Fully remote team with async-friendly work culture
• Work on cutting-edge real-world AI agent deployments
• Opportunity to own features and build IP from scratch
• Collaborate directly with the CEO & founding team
• Flexible hours, competitive pay, and high-impact projects

How to Apply

Send your resume, GitHub/portfolio, and a brief note on the most exciting GenAI project you've worked on to: [email protected]