Artificial Intelligence Engineer

Location: Bengaluru

AI Engineer

Profile Summary
AI Engineer focused on building and operating  LLM-powered solutions  for  legal and regulatory document workflows  (e.g., EU AI Act, DSA, Data Privacy, ESG, Security, Compliance). Strong emphasis on  reference identification & resolution ,  retrieval quality ,  traceability , and  evaluation  in document-centric AI systems.

Core Responsibilities / Focus
Design and implement  GenAI / Agentic AI  applications for complex document understanding and decision support
Build  RAG pipelines  tailored to regulatory/legal texts (high precision, citation grounding, explainability)
Develop robust ingestion and retrieval strategies, including  contextual chunking ,  embeddings , and metadata enrichment
Integrate  Knowledge Graphs (RDF/SPARQL)  with LLM workflows for structured + unstructured reasoning
Orchestrate multi-step AI workflows using  Lang Chain / Lang Graph  (and similar agent frameworks)
Establish  AI quality assurance  and evaluation practices (e.g., retrieval quality, hallucination checks, judge-based evals, RAGAS-style scoring)
Build & train / fine-tune  specialized NER-related models
Support  model lifecycle  activities (experimentation, versioning, deployment readiness, monitoring handover)

Core Skills (Must-Have)
Python  (primary)
Docker / Docker Compose
NLP / NLU
GenAI / LLM application development
Agentic AI
RAG (Retrieval-Augmented Generation)
Embeddings
Contextual chunking strategies
Knowledge Graphs (RDF)
SPARQL
Model lifecycle / ML application lifecycle
Lang Chain
Lang Graph
Git
AI QA / evaluation  (e.g., RAGAS, LLM judges, retrieval and answer quality validation)

Preferred / Nice-to-Have
Java
Kubernetes
Dev Containers
Git Ops
Documentation practices
Deepagents  (or similar advanced agent frameworks)

Domain Advantage

Experience with  legal, regulatory, compliance, and policy documents
Understanding of requirements around  auditability, explainability, and risk controls  in AI systems