AI/ML Engineer – LLM & Agentic Systems

Location: Bangalore, India (Full time) and Chennai,India (Full -time)

We are looking for a Senior AI/ML Engineer to design, build, and evaluate LLM-based systems that automate complex, multi-step healthcare workflows.

Key Responsibilities
Agentic Architecture: Design and own prompt/agent architectures and task decomposition for multi-step production healthcare workflows.
RAG Pipeline Engineering: Build and maintain advanced RAG pipelines utilizing semantic/hierarchical chunking, embedding optimizations, and vector database retrieval.
Evaluation & Guardrails: Build independent verification layers and evaluation harnesses (golden datasets, automated scoring, precision/recall/F1 tracking) using tools like Ragas or DeepEval.
Production Optimization: Drive down cost-per-transaction and latency in production; make model-selection tradeoffs between hosted APIs (OpenAI, Anthropic) and self-hosted models.
Cross-functional Collaboration: Partner with data engineering on dataset construction and quality stakeholders on production go-live criteria

Required Qualifications
Experience:



3 years of experience building and deploying production-grade LLM systems (not just wrapper prototypes or demos).
RAG Expertise: Hands-on experience with embedding strategies, vector databases (pgvector, OpenSearch, Pinecone, or Weaviate), and advanced chunking methods.
Evaluation Metrics: Demonstrated experience evaluating model tasks using quantitative frameworks (Precision, Recall, F1 score).
Cloud & Orchestration: Proficiency with a major cloud AI platform (AWS Bedrock/SageMaker, Azure OpenAI, or GCP Vertex AI) and orchestration tools (LangChain or LlamaIndex).
Core Skills: Solid Python capabilities along with basic microservice design (REST / gRPC) and containerisation (Docker, Kubernetes).

Preferred Qualifications
Experience in healthcare, insurance claims, or another highly regulated, zero-error-margin domain.
Familiarity with HIPAA compliance and PHI/PII data handling requirements (data masking/redaction).
Hands-on experience with LLM-as-a-judge observability tooling (LangSmith, Braintrust, DeepEval, Ragas, or promptfoo).

📌 Artificial Intelligence Engineer Bengaluru
🏢 Antal International
📍 Bengaluru