Job Title: AI Engineer

Location: Ahmedabad

Work Model: Work from Office

Experience: 3+ Years

Employment Type: Full-Time

About the Role

We are looking for an AI Engineer with 3+ years of experience to design, build, deploy, and maintain production-ready AI solutions. The ideal candidate should have strong hands-on experience in Generative AI, RAG, LLM application development, and AI engineering frameworks, with a proven track record of taking AI solutions from prototype to production.

This role requires someone who understands more than just prompting or experimenting with LLMs — you should be comfortable owning the complete AI solution lifecycle, including architecture, development, evaluation, deployment, monitoring, optimization, and security.

Key Responsibilities

- · Design and develop production-grade AI/GenAI solutions aligned with business requirements.
- · Build and optimize Retrieval-Augmented Generation (RAG) systems, including document ingestion, chunking, embeddings, vector search, retrieval, reranking, and response generation.
- · Develop LLM-powered applications using frameworks such as LangChain, LangGraph, LlamaIndex, or equivalent.
- · Design and implement AI solution architecture covering LLMs, APIs, databases, vector databases, orchestration, and external integrations.
- · Take AI solutions through the complete lifecycle: Design → Develop → Evaluate → Deploy → Monitor → Improve.
- · Implement LLM evaluation and quality measurement to assess accuracy, relevance, hallucination, latency, and overall system performance.
- · Apply AI security best practices, including prompt injection protection, data privacy, access control, secure API integration, and protection of sensitive information.
- · Optimize AI applications for accuracy, latency, scalability, reliability, and cost.
- · Integrate AI solutions with existing enterprise applications, APIs, databases,



and business workflows.
- · Collaborate with product, engineering, and business teams to translate requirements into scalable AI solutions.
- · Stay current with developments in LLMs, Generative AI, AI agents, RAG architectures, and AI engineering practices.

Required Skills & Experience

- · 3+ years of hands-on experience in AI/ML/Generative AI engineering.
- · Proven experience of building and deploying at least one AI/GenAI solution in a production workplace.
- · Strong understanding of the complete AI solution lifecycle, including architecture, development, evaluation, deployment, monitoring, and security.
- · Strong hands-on experience with RAG architecture and implementation.
- · Robust command of Python and experience building production-grade applications/services.
- · Hands-on experience with LangChain, LangGraph, LlamaIndex, or similar AI/LLM frameworks.
- · Good understanding of LLMs, embeddings, vector databases, semantic search, prompt engineering, and context management.
- · Experience working with vector databases such as Pinecone, Weaviate, Qdrant, Milvus, Chroma, FAISS, or equivalent.
- · Experience working with LLM providers/models such as OpenAI, Azure OpenAI, Anthropic, Gemini, Llama, or equivalent.
- · Understanding of LLM evaluation, observability, monitoring, and performance optimization.
- · Understanding of AI/LLM security risks, including prompt injection, data leakage, insecure tool usage, and access control.
- · Good understanding of REST APIs,



databases, Git, Docker, and cloud environments.
- · Ability to write clean, maintainable, testable, and production-ready code.

Good to Have

- · Experience building AI Agents / Agentic AI / multi-agent workflows using LangGraph or similar frameworks.
- · Experience with AI evaluation frameworks such as Ragas, DeepEval, LangSmith, or equivalent.
- · Experience with LLM observability and tracing.
- · Experience deploying AI applications using AWS, Azure, or GCP.
- · Knowledge of CI/CD, Kubernetes, serverless architecture, or MLOps/LLMOps.
- · Experience with fine-tuning, model adaptation, or open-source LLM deployment.
- · Experience integrating AI solutions with enterprise systems and business workflows.

What We Are Looking For

The ideal candidate is not someone who has only experimented with ChatGPT, prompts, or basic RAG projects. We are looking for an engineer who can demonstrate:

- · A real production AI solution they have personally contributed to or owned.
- · Strong understanding of why and how the AI architecture was designed.
- · Hands-on expertise in RAG and LLM application development.
- · Ability to evaluate and improve AI output quality rather than relying solely on subjective testing.
- · Awareness of security, scalability, reliability, latency, and cost considerations in production AI systems.
- · Strong engineering fundamentals and the ability to convert AI concepts into robust, maintainable software.

Thanks and regards,

Team Fx31labs

Pay: ₹478,159.42 - ₹1,080,665.16 per year

Benefits:

- Flexible schedule

Ability to commute/relocate:

- Ahmedabad, Gujarat: Reliably commute or planning to relocate before starting work (Preferred)

Experience:

- AI Engineer: 2 years (Required)
- Gen AI, RAG pipeline: 2 years (Required)

Work Location: In person

📌 AI Engineer (India)
🏢 Fx31 Labs
📍 India