Lead Engineer

R Systems; Bengaluru Urban; On-site; INR 3,000,000 - 5,400,000; Full time

Job summary

R Systems in Bengaluru, India seeks a senior AI/ML engineer to design and ship production-grade LLM-powered applications. You will build end-to-end RAG systems, craft prompts, and develop agentic workflows with multi-step task execution and safeguards.

Strong Python, cloud, and tooling fluency are required, with focus on reliability and scalable evaluation. The role emphasizes working with unstructured data, tool calling, and self-hosted serving options, including Docker-based deployments in

Qualifications

• 6+ years of software engineering experience with 3+ years shipping LLM-powered apps.
• Strong Python skills with production-quality code and typed data modeling.
• Hands-on production experience with major LLM providers and tool calling.
• Experience building RAG systems incl. embeddings, vector stores, and retrieval.
• Experience building agentic workflows with multi-step autonomous tasks.
• Experience with fine-tuning/adaptation (LoRA, QLoRA, instruction tuning).
• Fluent LLM tooling with LangChain, LangGraph, LlamaIndex, DSPy, and HF.
• Prompt engineering for system prompts, few-shots, and structured outputs.
• Comfort with unstructured data extraction, classification, and structured output generation.
• Cloud and deployment fluency (AWS preferred, Bedrock, Docker).
• Experience with testing non-deterministic systems and evaluating outputs.
• Strong debugging for LLM failures (hallucinations, retrieval gaps, latency).

Skills

Python

LLM integration

RAG systems

LLM agents

Fine-tuning

LangChain

Prompt engineering

unstructured data

AWS Bedrock

Docker

Tools

Qdrant

Pinecone

Weaviate

OpenSearch

pgvector

LlamaIndex

DSPy

Hugging Face

LangGraph

Job description

Core Experience

• 6+ years of software engineering experience, with 3+ years building and shipping LLM-powered applications in production.
• Strong Python skills — production-quality code, clean architecture, type-safe data modeling (Pydantic or equivalent), and testable design.
• Hands-on production experience with at least one major LLM provider — AWS Bedrock, Anthropic Claude, OpenAI GPT, Google Gemini, or equivalent — including tool/function calling and structured output.
• Demonstrated experience building RAG systems end to end — chunking, embeddings, vector databases (Qdrant, Pinecone, Weaviate, OpenSearch, or pgvector), retrieval, and re-ranking.
• Hands-on experience building agentic workflows — LLM agents that call tools, reason across multiple steps, and autonomously complete multi-stage tasks with appropriate safeguards.
• Experience with fine-tuning and adaptation workflows — LoRA, QLoRA, instruction tuning, or preference tuning — and with evaluating model outputs rigorously rather than by demo.
• Solid LLM tooling fluency — LangChain or LangGraph, LlamaIndex, DSPy, Hugging Face, and the judgment to pick the right tool rather than adopt reflexively.
• Prompt engineering craft — system prompts, few-shot examples, chain-of-thought, structured output schemas, and tool/function calling.
• Comfort working with unstructured data — extracting, classifying, and generating structured outputs from text-heavy inputs, including documents and forms.
• Cloud and deployment fluency — AWS preferred (including Bedrock), plus containerization (Docker), and familiarity with self-hosted LLM serving (vLLM, TGI, Ollama, or similar).
• Evaluation discipline — ability to write tests for non-deterministic systems, build golden sets, and reason about output quality at scale.
• Strong debugging instincts for LLM-specific failure modes — hallucinations, retrieval gaps, prompt drift, and latency spikes.

Security & Regulated-Industry Awareness

• Working awareness of LLM security concerns — prompt injection, data exfiltration, output filtering, and PII handling.

Preferred Qualifications

• Experience in fintech, lending, banking, healthcare, or another regulated or data-sensitive industry.
• Familiarity with document understanding models (LayoutLM, Donut, Nougat) and modern OCR tooling (Textract, Tesseract, or equivalents).
• Background in NLP tasks such as named entity recognition, classification, or semantic similarity.
• Experience with LLaMA-family open-weight models and self-hosted serving via Ollama or vLLM.
• Experience contributing to a shared AI platform (prompt registry, evaluation harness, routing layer) used by multiple product teams.