AI Developer

Job Title: AI Developer (LLM & RAG)

Location: Remote

Experience Required: 5–7 years

Employment Type: Full-time

About the Role

We are looking for a highly skilled AI Developer with deep expertise in Large Language Models (LLMs), Retrieval-Augmented Generation (RAG), and AI application development. The ideal candidate will have hands-on experience building end-to-end Generative AI solutions by orchestrating foundation models, integrating vector databases, and deploying scalable LLM-powered systems for real-world business use cases.

You’ll collaborate closely with our product and engineering teams to design intelligent assistants, copilots, and automation systems that leverage the latest in OpenAI, Anthropic, Hugging Face, LangChain, and vector databases.

Key Responsibilities

* Design and implement RAG pipelines that combine LLMs with structured/unstructured knowledge bases.

* Develop LLM-powered applications using frameworks such as LangChain, LlamaIndex, or Haystack.

* Integrate and manage vector databases (Pinecone, Weaviate, Milvus, Qdrant, FAISS) for semantic search and context retrieval.

* Fine-tune and prompt-engineer foundation models (GPT-4, Claude, Gemini, Llama) for domain-specific use cases.

* Build AI microservices and APIs to embed intelligence into existing products and platforms.

* Collaborate with cross-functional teams to deploy, monitor, and optimize production-grade AI workflows.

* Implement evaluation metrics, feedback loops, and continuous improvement strategies for LLM outputs.

* Stay current with emerging tools, frameworks, and APIs in the Generative AI ecosystem.

Desired Skills & Experience

* 5–7 years of experience in AI/ML/NLP development, with at least 2+ years in LLM-based systems.

* Proficiency with Python, LangChain, LlamaIndex, FastAPI, and prompt engineering.

* Hands-on experience with cloud AI platforms(AWS Bedrock, Azure OpenAI, GCP Vertex AI).

* Strong knowledge of RAG architectures, vector search, and embedding models.

* Familiarity with MLOps/AIOps practices and containerized deployments (Docker, Kubernetes).

* Understanding of data preprocessing, knowledge graphing, and context injection techniques.

* Bonus: Experience building chatbots, copilots, or AI assistants for HR, finance, or customer support domains.

Why Join Us?

100% remote opportunity with flexible work hours.

Work on cutting-edge LLM and GenAI projects with global impact.

Collaborative, innovative, and fast-paced environment.

Competitive compensation and benefits.

If you’re passionate about pushing the boundaries of AI and creating impactful GenAI solutions, we’d love to hear from you!