Job highlights

- 3-4 years experience in LLM primitives, prompt engineering, RAG architectures, vector databases, and Python backend development

- Design and deploy LLM-based agent frameworks, build multi-agent networks, optimize vector data and models, develop scalable Python backends and APIs, implement model observability and evaluation

Job Overview:

We are looking for a highly motivated AI Engineer with 3-4 years of experience to design, implement, and optimize cutting-edge AI solutions. In this full-time, on-site role based in Ahmedabad, you will be among the first engineers building a foundational stack at the intersection of AI agents, voice interfaces, consumer hardware, regional languages, and system-level app integrations (WhatsApp, UPI, instant commerce). This position is tailored for engineers passionate about large language model (LLM) integration, stateful multi-agent orchestrations, and robust backend engineering.

Key Responsibilities:

- Agent Frameworks &
- LLM Integration: Architect and deploy advanced LLM-based features using state-of-the-art frameworks such as LangChain, LangGraph, AutoGen, and CrewAI.

- Multi-Agent &

- RAG Pipeline Engineering: Design production-grade multi-agent networks, autonomous tool-augmented workflows, memory components, and retrieval-augmented generation (RAG) loops.

- Vector Data &

- Model Architecture:



Manage, query, and optimize vector databases (e.g., Pinecone, Weaviate, FAISS) alongside fine-tuning models and embeddings with Hugging Face Transformers.

- Backend &

- API Development: Build high-performance, scalable Python backends and secure REST APIs to serve as the core orchestration layer for hardware and voice automation pipelines.

- Model Observability &

- Evaluation: Implement end-to-end evaluation, prompt tracing, drift tracking, and model debugging frameworks using platform toolsets like LangSmith.

Required Skills &

- Qualifications:

- 3-4 years of functional engineering experience with transparent, practical knowledge of LLM primitives, prompt engineering, and agentic workflows.

- Hands-on exposure to retrieval-augmented generation architectures, semantic vector space search, and vector storage engines.

- Strong programming command over Python, backend software development architectures, and scalable API design patterns.

- Solid architectural comprehension of multi-agent execution graphs, state machine orchestration, and persistent agent memory patterns.

- B.E. / B.Tech or equivalent technical undergraduate degree in Computer Science, Artificial Intelligence, or a highly quantitative engineering field.

📌 Artificial Intelligence Engineer (Ahmedabad)
🏢 Nxtwave Disruptive Technologies (Hiring for a client)
📍 Ahmedabad