Role Overview:
We are looking for a hands-on AI Engineer with 2–3 years of experience to design, build, and
deploy Generative AI and machine learning powered applications. The ideal candidate should
be comfortable working with LLMs, embeddings, vector databases, and agent-based workflows
and should have experience integrating AI models into production systems and enterprise
workflows.
This role is application-engineering focused (not pure research). You will be building real AI
products such as chatbots, copilots, document intelligence systems, and knowledge assistants
using modern GenAI frameworks.
Key Responsibilities:
LLM & Generative AI Development
Build AI applications using LLMs (OpenAI, Gemini, Llama, Claude, or similar)
Implement RAG (Retrieval Augmented Generation) pipelines
Perform prompt engineering, prompt tuning, and evaluation of responses
Develop conversational AI assistants, copilots, and automation agents
Handle hallucination reduction, grounding, and response quality improvement
AI Application Engineering:
Use LangChain / LangGraph / CrewAI or similar agent frameworks
Integrate LLMs with APIs, databases, and enterprise applications
Build document processing systems (PDF, emails, knowledge bases)
Develop multi-step reasoning workflows and AI agents
Implement tool-using agents (search, database querying, workflows)
Data & Vector Infrastructure:
Create embeddings and semantic search pipelines
Work with vector databases such as:
o Pinecone / FAISS / ChromaDB / PostgreSQL (pgvector)
Implement chunking strategies, indexing, and retrieval optimization
Build scalable ingestion pipelines
Model Operations & Deployment:
Deploy models and applications via APIs and containers
Track and manage experiments using MLflow or similar
Monitor performance, latency, and response accuracy
Optimize token usage and inference cost
Implement evaluation metrics and feedback loops
Required Skills:
Programming & Core Tech
Python (must have)
Strong understanding of APIs, REST services, JSON
Git and version control
Basic SQL & database querying
AI/ML & GenAI:
Experience with LLM APIs (OpenAI / Azure OpenAI / Gemini / HuggingFace)
Prompt engineering and evaluation
Embeddings and semantic search
RAG architecture understanding
Familiarity with hallucination mitigation techniques
Frameworks & Tools:
LangChain or LangGraph
Vector databases (FAISS / Pinecone / ChromaDB / pgvector)
Transformers / HuggingFace (basic usage)
FastAPI / Flask for serving models
Docker (basic level)
Good to Have:
Knowledge of agent frameworks (CrewAI, AutoGen)
Web search grounding (Tavily or similar)
MCP (Model Context Protocol) usage
Basic cloud exposure (AWS / Azure / GCP)
Streamlit or Gradio UI apps
Fine-tuning or LoRA knowledge
Educational Qualification:
B.Tech / BE / MS in Computer Science, AI, Data Science, or related field
Relevant certifications or GenAI coursework preferred