Description :

Location : Indore (Onsite)

Experience : 2+ Years

Employment Type : Full-Time

Company : Supersourcing/ Engineer Babu

About Engineer Babu :

We are a CMMI Level 5 certified group specializing in custom app and website design, AI-powered solutions, cross-platform apps, and enterprise systems. With deep expertise in SaaS, DevOps, and software development. Our proven methodologies reduce risks and enhance value - achieving up to 40% task automation and 25% efficiency gains. Clients trust us for exceeding expectations and consistently delivering measurable results.

Role Overview :

We are looking for an AI Engineer with strong expertise in Large Language Models (LLMs), Retrieval-Augmented Generation (RAG), and LLM application frameworks to build scalable, production-grade AI systems. The role focuses on designing intelligent AI applications, including context-aware systems, semantic retrieval pipelines, and safe/controlled LLM deployments using guardrails.

Key Responsibilities :

LLM Application Development :

- Design and develop LLM-powered applications for real-world use cases

- Build systems for context-aware reasoning, summarization, and generation

- Implement prompt engineering and structured output pipelines

RAG & Retrieval Systems :

- Design and implement Retrieval-Augmented Generation (RAG) pipelines

- Work with embeddings and semantic search for high-quality retrieval

- Optimize chunking, indexing, and retrieval strategies for performance and accuracy

LLM Frameworks & Orchestration :

- Build applications using frameworks like :

1. LangChain

2. LlamaIndex

- Implement agent-based workflows and tool integrations

- Design modular and scalable LLM pipelines

Guardrails, Safety & Evaluation :

- Implement LLM safety mechanisms using tools like :

1. Guardrails AI

2. NeMo Guardrails

- Build validation, filtering, and output control systems

- Evaluate LLM responses for quality, hallucination, and reliability

Vector Databases & Search :

- Work with vector databases such as :

1. Pinecone

2. Weaviate

3. FAISS

- Optimize similarity search, indexing, and retrieval latency

Deployment & MLOps :

- Deploy LLM applications on cloud platforms like :

1. Amazon Web Services

2. Microsoft Azure

3. Google Cloud Platform

- Build scalable APIs and microservices for LLM inference

- Use Docker, Kubernetes for deployment and orchestration

- Implement monitoring, logging, and performance tracking

Required Skills & Qualifications :

- 2-4 years of experience in AI/ML or backend engineering with LLM exposure

- Strong proficiency in Python

- Hands-on experience with LLMs, prompt engineering, and fine-tuning

- Strong experience in RAG pipelines and semantic search systems

- Experience with LangChain / LlamaIndex or similar frameworks

- Solid understanding of vector databases and embeddings

- Experience in building production-grade AI/ML systems

- Good understanding of APIs, system design, and scalability

- Exposure to cloud deployment and MLOps practices

Good to Have :

- Experience with LLM agents and tool-usage workflows

- Exposure to evaluation frameworks and LLM benchmarking

- Familiarity with streaming responses and real-time AI systems

- Knowledge of cost optimization for LLM systems