AI Engineer

Role Overview

We are looking for an AI Engineer with strong hands-on experience in Generative AI, LLMs, RAG, and conversational AI. The candidate will design and develop production-grade AI solutions using LLMs, retrieval pipelines, and agentic AI frameworks.

Responsibilities

• Build production-ready LLM-based conversational agents with tool/function calling, dialogue state, guardrails, and safety.
• Design and develop RAG pipelines including indexing, chunking, embeddings, reranking, and hybrid search.
• Develop document AI solutions for complex PDFs, images, tables, and scanned documents using OCR and multimodal LLMs.
• Design and optimize prompts, system instructions, templates, and few-shot examples.
• Evaluate AI solutions for grounding, hallucination, latency, and cost.
• Deploy and monitor AI applications on AWS / Azure / GCP.
• Work with business and technical stakeholders to understand requirements and deliver AI solutions.
• Prepare technical documentation, test plans, runbooks, release notes, and project updates.

Requirements

• 4–6 years of experience in AI/ML application development.
• 1–2+ years of hands-on experience with LLMs and RAG.
• Strong Python programming skills.
• Experience with LangChain / LlamaIndex / Hugging Face.
• Hands-on experience with vector databases such as Qdrant, Milvus, or Elasticsearch.
• Strong understanding of semantic search, embeddings, reranking, and chunking strategies.
• Experience with OCR, table extraction, document/layout parsing, and multimodal LLMs.
• Experience with MCP or similar agent/tool integration frameworks.
• Knowledge of Prompt Engineering, Cloud deployment, Containers, and CI/CD.
• Strong client/business-facing communication skills.

Skills

• Python
• LangChain
• LLMs
• RAG
• Vector Databases

Good to Have

• Experience in Agentic AI / Generative AI.
• Pharmaceutical / Healthcare industry experience.
• Experience handling customer/client-facing workshops and discussions.

Benefits

• Paid time off
• Provident Fund