4-7 years of experience in Data Science / Applied ML / NLP with hands-on GenAI delivery.
Strong Python skills; experience with FastAPI/Flask (or similar) for serving.
Practical experience with LLMs, including:
RAG pipelines (vector DB + embeddings + retrieval + grounding)
Prompt engineering and structured outputs (JSON schema/function calling patterns)
Experience building or integrating agents/tool-use systems (planning + tool execution + retries + state management).
Knowledge of NLP fundamentals: tokenization, embeddings, similarity search, ranking.
Proficiency with SQL and data processing (pandas / Spark basics).
Experience with LangChain / LlamaIndex / Semantic Kernel (or similar orchestration frameworks).
Familiarity with vector databases: Weaviate/PGVector
Knowledge of LLM safety: prompt injection defense, data exfiltration prevention, moderation filters, sandboxing tools.
Experience with cloud platforms: Azure especially managed AI services.
Familiarity with MLflow, Weights & Biases, or similar tracking tools.
Tech Stack
Languages: Python, SQL
LLM/GenAI: OpenAI/Azure OpenAI or open-source (Llama/Mistral), Hugging Face
Orchestration: LangChain / LlamaIndex / Semantic Kernel
Vector Search: Weaviate/PGVector
Backend: FastAPI, Docker, Kubernetes (optional)
MLOps/Obs: MLflow/W&B, Prometheus/Grafana, Open Telemetry (optional)
Data: Postgres, S3/ADLS