Lead discovery and solution design for GenAI use cases, translating business problems into concrete architectures (LLM decision, RAGs, fine‑tuning, agents, guardrails)
Build end‑to‑end GenAI applications: data ingestion, retrieval layer, orchestration (e.g. LangChain/LlamaIndex/LangGraph), API/backend, and simple UI where needed.
Design and implement RAG pipelines with vector databases, hybrid search, rerankers, query transformation, and evaluation frameworks for relevance and robustness.
Perform model selection, prompting strategies, and fine‑tuning (LoRA/QLoRA/SFT) for text, code, and multimodal models, including evaluation and A/B testing.
Implement safety, compliance, and governance controls (input/output filters, PII handling, audit logs, human‑in‑the‑loop review where required).
Collaborate with data engineers, product owners, and full‑stack developers on scalable architectures, SLAs, and integration with existing enterprise systems
Gather technical requirements and estimate planned work.
Mentor other data scientists/engineers in GenAI patterns, code quality, and best practices; contribute to internal libraries, templates, and reusable components.
Stay current with GenAI landscape (new open and hosted models, agentic frameworks, evaluation techniques) and perform targeted PoCs to validate them.
Requirements
6+ years of experience in Data Science/AI engineering
At least 4+ years of experience in production-ready Python AI-related code development.
At least 2+ years of experience in production-ready LLM-related code development, preferably based on the Retrieval-Augmented Generation (RAG) concept.
Strong analytical and problem-solving skills with the ability to optimize AI solutions for diverse applications.
Strong knowledge and experience in Generative AI, including LLMs, chatbots, AI agents, and RAG mechanisms.
Deep understanding of LLM evaluators, validators, and guardrails.
Hands‑on experience with one or more GenAI frameworks: LangChain, LlamaIndex, LangGraph, or similar orchestration stacks.
Hands-on experience designing or operating MCP servers/clients for LLM agents
Strong Python skills, including production grade code, packaging, and testing for data/ML services
Solid understanding of ML/AI concepts: types of algorithms, machine learning frameworks, model efficiency metrics, model lifecycle, AI architectures.
Proven ability to collaborate effectively across technical and non-technical teams.
Familiarity with cloud environments such as Azure (preferred), GCP, or AWS, including AI-related managed services.
Familiarity with CI/CD, testing, and containerized deployments.
Excellent communication skills in English, with the ability to convey complex technical concepts to various audiences.