Job Description: Generative AI Engineer
Location: Remote / Bangalore
Employment Type: Full-time
Department: AI & Research
Industry: IT Services & Consulting
Role Category: AI/ML – Generative AI
Role & Responsibilities:
As a Generative AI Engineer, you will be responsible for designing, developing, and deploying generative AI models, large language model (LLM) applications, and agentic flows.
Your core responsibilities will include:
- Build Production RAG/Agentic Flows: Develop and implement advanced retrieval-augmented generation (RAG) flows, including tasks like chunking/embeddings, retrieval, tool/function calling, and caching for scalable AI solutions.
- Evaluation Harnesses: Implement evaluation frameworks to assess model quality based on key metrics such as groundedness, relevance, and completeness.
Perform regression checks to ensure the stability of models over time. - Guardrails & Content Safety: Integrate content safety measures, guardrails, and proactive monitoring systems to ensure responsible AI usage.
You will be responsible for documenting prompts/configs and optimizing for cost and latency considerations. - API/SDK Development: Develop and ship high-performance APIs/SDKs used by both web and mobile teams, ensuring seamless integration of AI-driven features.
- Cross-functional Collaboration: Collaborate with different teams to ensure that the AI solutions meet the needs of the business while maintaining high quality and compliance standards.
Desired Candidate Profile:
- Experience: 1–2 years of experience in backend/application development with a focus on AI/ML systems, especially in Generative AI, LLMs, and AI-powered applications.
- Technical Skills:
- Proficiency in backend programming languages like Python or TypeScript.
- Practical experience working with Generative AI models, especially around model deployment, prompt engineering, and scaling solutions.
- Familiarity with Vector Databases (e.g., Pinecone, Weaviate) for managing embeddings and data retrieval.
- Experience with tools like LangChain or LlamaIndex for building AI-powered systems.
- Understanding of caching strategies to optimize system performance.
- Knowledge of observability principles and tracing techniques to monitor AI model performance in production environments.
- Education:
- B.E/B.Tech/M.E/M.Tech/MCA or equivalent in Computer Science, AI, Data Science, or a related field.
Key Skills:
- Generative AI
- RAG (Retrieval-Augmented Generation)
- LLMs (Large Language Models)
- Embeddings
- Vector Databases (e.g., Pinecone, Faiss)
- Prompting Techniques
- LangChain/LlamaIndex
- FastAPI
- Node.js/TypeScript
- Caching
- Observability
- Model Deployment
- Content Safety
- Monitoring & Analytics
- Backend Development (Python/TypeScript)
Notice Period:
- Immediate to 30 days preferred.
#GenerativeAI #BackendDevelopment #LLMs #AI #AIEngineer #RAG #Embeddings #VectorDB #LangChain #LlamaIndex #Python #TypeScript #API #Caching #Observability #AIResearch #ContentSafety #FastAPI #NodeJS #TechJobs #RemoteJobs #BangaloreJobs #AIinIT #ITConsulting #MachineLearning #AIandML