Job Title: AI Engineer – LLM / RAG / Agentic AI
Experience: 3+ Years
Location: Remote Preferred
Employment Type: Contract
Contract Duration: 12+ Months / Long-Term Engagement
Work Timings: To be discussed
Job Summary
We are looking for an experienced AI Engineer with strong hands-on expertise in building and deploying LLM-powered applications, RAG systems, AI agents, document intelligence solutions, and cloud-based AI applications.
The ideal candidate should have at least 3+ years of experience in ML/AI application development, including 1–2+ years of practical experience with LLMs and Retrieval-Augmented Generation (RAG).
This is a long-term contract opportunity for candidates who can independently design, develop, evaluate, deploy, and improve production-grade AI solutions.
Key Responsibilities
- Design and implement LLM agents with:
- Tool calling
- Function calling
- Dialogue state
- Guardrails
- Safety controls
- Build high-quality RAG and retrieval pipelines involving:
- Document indexing
- Chunking
- Embeddings
- Vector search
- Hybrid retrieval
- Reranking
- Ingest and process complex documents and PDFs.
- Implement OCR and multimodal LLM-based document/image understanding.
- Handle complex document structures including:
- Tables
- Layouts
- Images
- Mixed-format content
- Design and optimize prompts, prompt templates, and few-shot examples.
- Conduct A/B testing and automated LLM evaluations.
- Measure and optimize:
- Grounding
- Hallucination
- Accuracy
- Latency
- Cost
- Deploy and monitor AI applications on cloud platforms.
- Implement appropriate observability and monitoring.
- Integrate AI agents with external tools and enterprise data sources.
- Create and maintain technical documentation, requirements, designs, and user guides.
Mandatory Skills
- 3+ years of experience building AI / ML applications.
- At least 1–2+ years of hands-on LLM and RAG experience.
- Strong programming expertise in Python.
- Hands-on experience with:
- LangChain and/or LlamaIndex
- Hugging Face
- Strong experience with vector databases such as:
- Qdrant
- Milvus
- Elasticsearch
- Or equivalent vector search platforms
- Strong understanding of RAG architecture.
- Practical experience with:
- Chunking strategies
- Embedding model selection
- Embedding tuning
- Vector retrieval
- Hybrid search
- Reranking
- Experience processing complex PDFs and documents.
- Experience with table extraction and document layout parsing.
- Experience with OCR and/or multimodal AI document understanding.
- Experience integrating tools and external data sources using MCP or similar protocols/frameworks.
- Strong knowledge of Prompt Engineering.
- Hands-on cloud deployment experience with AWS, Azure, or GCP.
- Positive understanding of AI evaluation, observability, latency, and cost optimization.
Nice to Have
- Experience with Generative AI and Agentic AI systems.
- Knowledge of AI agents and autonomous workflows.
- Experience implementing AI guardrails and safety mechanisms.
- Experience with LLM evaluation frameworks.
- Experience working in the Pharmaceutical / Life Sciences domain.
Ideal Candidate
We are looking for a hands-on AI Engineer who can own AI solutions from:
Requirement Understanding → Architecture → Development → RAG/Agent Implementation → Evaluation → Cloud Deployment → Monitoring → Optimization
Candidates with strong practical experience in Python, LLMs, RAG, LangChain/LlamaIndex, Hugging Face, vector databases, document intelligence, MCP, prompt engineering, and cloud deployment will be highly preferred.
How to Apply
Interested candidates can share their updated resume at:
[email protected]
Pay: ₹60,000.00 - ₹70,000.00 per month
Work Location: Remote
📌 AI Engineer – LLM / RAG / Agentic AI (India)
🏢 Kasmoprav
📍 India