Role Overview:

This is a production-oriented Gen AI opportunity focused on building LLM-based applications rather than just prompt engineering or chatbot development.

Core Skills (Must-have):

- Hands-on experience building Gen AI / LLM-based applications

- Strong Python programming skills

- Prompt engineering and working with LLM APIs (OpenAI, Anthropic, etc.)

- Experience with RAG pipelines, embeddings, and vector databases

- Familiarity with Gen AI frameworks such as LangChain or LlamaIndex

- Good understanding of software engineering practices (Git, code reviews, testing)

Preferred Skills:

- Experience designing and building reusable Gen AI authoring frameworks or accelerators

- Templatization of prompts, workflows, and agent configurations

- Containerization and deployment on Kubernetes (EKS or similar)

- Working with databases (SQL/NoSQL) and vector stores

- CI/CD pipelines and deployment automation

- Exposure to cloud services (AWS preferred), API development, and observability/monitoring

Role Expectations:

The candidate will debug issues on the existing platform, update the codebase, and engage directly with clients on both business and technical requirements.

Ideal Candidate Profile:

- Strong Python coding skills

- Experience building production-grade Gen AI applications

- Expertise in LangChain/LlamaIndex and Vector databases (Pinecone, Chroma, Weaviate, FAISS, etc.)

- RAG implementation experience

- AWS + Kubernetes deployment exposure

- Client-facing communication skills