- Design and build applications powered by large language models (LLMs)
- Develop retrieval-augmented generation (RAG) pipelines using vector databases
- Fine-tune and optimize prompts for accuracy, cost, and latency
- Integrate LLM APIs (OpenAI, Anthropic, open-source models) into products
- Evaluate model outputs and build guardrails for safety and reliability
- Collaborate with product teams to identify high-impact GenAI use cases
- Stay current with the fast-evolving GenAI ecosystem and tooling
Required Skills:
- Strong programming skills in Python
- Hands-on experience with LLM frameworks (LangChain, LlamaIndex)
- Understanding of prompt engineering and RAG architecture
- Experience with vector databases (Pinecone, Weaviate, FAISS)
- Familiarity with LLM APIs (OpenAI, Anthropic, Hugging Face)
- Understanding of embeddings and semantic search
- Good grasp of software engineering fundamentals
Valuable to Have:
- Experience fine-tuning open-source LLMs
- Knowledge of AI safety and evaluation frameworks
- Exposure to multi-agent systems
About the Opportunity:
This is a full-time, permanent role with excellent growth prospects. The client offers a collaborative work culture, competitive compensation, and strong learning opportunities.