Key Responsibilities
Develop and deploy Generative AI applications using LLMs (GPT, Llama, etc.)
Build and maintain LLM pipelines, including prompt engineering and fine-tuning
Design and implement end-to-end AI/ML workflows (data → model → deployment)
Work with vector databases for semantic search and retrieval (RAG architecture)
Implement LLMOps practices for monitoring, evaluation, and versioning
Integrate LLMs into applications via APIs and microservices
Optimize model performance, cost, and latency
Collaborate with data engineers, product teams, and stakeholders
Conduct testing, validation, and debugging of AI models
Ensure security, compliance, and responsible AI practices
Required Skills & Qualifications
Technical Skills
Strong proficiency in Python
Hands-on experience with Generative AI & LLM frameworks:
OpenAI / Azure OpenAI APIs
Hugging Face Transformers
LangChain / LlamaIndex
Experience with prompt engineering and RAG (Retrieval-Augmented Generation)
Familiarity with vector databases (FAISS, Pinecone, Weaviate, Chroma)
Knowledge of ML/DL frameworks (PyTorch / TensorFlow – basics)
Experience in API development (FastAPI, Flask)
Understanding of RESTful services and microservices architecture
Preferred Skills (Nice-to-Have)
Experience with fine-tuning LLMs / parameter-efficient tuning (LoRA, PEFT)
Knowledge of multimodal AI (text, image, audio)
Exposure to cloud platforms (AWS, Azure, GCP)
Experience with Kubernetes and scalable deployments
Knowledge of data engineering tools (Spark, Kafka)
Familiarity with vector search optimization and embeddings
Understanding of AI governance, ethics, and compliance
Experience with chatbots, copilots, or conversational AI systems
Source: Infosys careers — Read the original posting and apply
This role is listed by the employer on its own careers site. Kaam Ki Khoj does not process applications for it.
Upload your CV once — we read it, build your profile and put you in front of every employer hiring on Kaam Ki Khoj. No forms, no fees.