AI Engineer (GenAI / LLMs / RAG)
Description
Role Overview:
- We are seeking an AI Engineer to design and deploy generative AI solutions, including LLM-based applications and Retrieval-Augmented Generation (RAG) pipelines, to solve real business problems.
Key Responsibilities:
- Design and implement LLM-powered applications (chatbots, copilots, agents).
- Build and optimize RAG pipelines (chunking, embeddings, retrieval, reranking).
- Fine-tune and evaluate LLMs for domain-specific use cases.
- Integrate AI solutions into production systems via APIs.
- Monitor model performance, cost, and latency in production.
Requirements:
- 3+ years of experience in AI/ML, with 1+ year focused on GenAI/LLMs.
- Strong understanding of prompt engineering and embedding-based retrieval.
- Experience with vector databases and orchestration frameworks.
- Familiarity with LLM evaluation and hallucination mitigation techniques.
Technical Stack / Tools:
- Python, LangChain, LlamaIndex.
- OpenAI, Anthropic, or open-source LLMs (Llama, Mistral).
- Vector databases (Pinecone, Weaviate, pgvector).
- Docker, FastAPI, cloud AI services (Azure OpenAI, AWS Bedrock, GCP Vertex AI).
Location: Remote - Anywhere
Skills required for this job:
- Application Programming Interface (API)
- Artificial intelligence (AI)
- Docker
- Generative artificial intelligence (Generative AI)
- LangChain
- Large language model (LLM)
- LlamaIndex
- ML
- Prompt engineering
- Python
- Retrieval-augmented generation (RAG)
- Vector databases