What You'll Be Doing:
Support build end-to-end GenAI applications such as chatbots, voicebots, Talk-to-Data systems, where you will help buiild: data ingestion, retrieval layer, orchestration (e.g. LangChain/LlamaIndex/LangGraph), API/backend, and simple UI where needed.
Implement RAG pipelines with vector databases, hybrid search, rerankers, query transformation, and evaluation frameworks for relevance and robustness.
Perform model selection, prompting strategies, and finetuning (LoRA/QLoRA/SFT) for text, code, and multimodal models, including guardrails, output evaluation and A/B testing.
Integrating and optimizing LLMs interaction with external tools, APIs, and data sources in a standardized and scalable way by using Model Context Protocol (MCP) connectors
Business understanding and translating problems into technical goals by defining tasks, auditing data feasibility, and highlighting issues.
Supporting project delivery
What We’re Looking For:
Familiarity with theory behind various deep learning concepts
Experience with Machine Learning (ML), especially in Generative AI (LLM/LMM) with focus on Natural Language Processing (NLP) or multimodal models.
Fluency in Python and object programing, working knowledge of SQL and vector database
Tech stack in Azure or GCP cloud
Knowledge of specific Deep Learning and GenAI libraries like: NumPy, PyTorch, HuggingFace, LangChain, LangGraph and GenAI APIs i.e. OpenAI/Gemini.
Experience with microservice architectures
Experience with code repositories and code assistants
Strong business acumen
Ability to come up with creative solutions to address customer problem
Nice to have:
Experience in working with Databricks will be a plus
Commercial experience proven by multiple successful projects in Generative AI, Natural Language Processing or Computer Vision will be a big plus
