Generative AI Engineer

RecruitBots AI; India; On-site; INR 1,200,000 - 2,800,000; Full time

Job summary

RecruitBots AI is seeking a Generative AI Engineer with 2–4 years of experience to build AI-powered applications using large language models and modern generative AI tools. You will collaborate with AI, engineering, and product teams to implement retrieval and reasoning workflows and deliver real-world AI solutions.

The role covers RAG, AI agents, prompt engineering, semantic search, and production-grade generative AI systems.

Qualifications

• Strong Python programming skills.
• Experience building AI-powered apps with LLMs.
• Knowledge of LLM APIs, prompt engineering, and structured outputs.
• Experience with REST APIs and integrating AI services.
• Understanding of embeddings, vector search, and RAG.
• Familiarity with databases and data processing.
• Knowledge of AI evaluation concepts: latency, reliability, cost.
• Familiarity with Git, testing, debugging, version control.
• Ability to investigate model failures and improve app behavior.
• Strong analytical and problem-solving skills.
• Team collaboration with AI, engineering, product.

Responsibilities

• Design, develop, and deploy Generative AI applications using modern LLMs and AI frameworks.
• Build LLM-powered applications for information retrieval, content generation, summarization, and intelligent automation.
• Develop RAG pipelines using document ingestion, chunking, embeddings, retrieval, and reranking techniques.
• Build AI agents that use tools, interact with APIs, and execute multi-step workflows.
• Design, test, and optimize prompts, system instructions, structured outputs, and tool-calling strategies.
• Integrate foundation models and AI services into backend applications and business workflows.
• Implement context management, conversation memory, and knowledge retrieval where required.
• Evaluate LLM outputs for accuracy, relevance, groundedness, consistency, and task completion.
• Investigate hallucinations, retrieval failures, prompt weaknesses, and unexpected model behavior.
• Optimize inference latency, token usage, response quality, and operational costs.
• Implement appropriate validation, guardrails, and fallback mechanisms to improve AI reliability.
• Develop automated evaluation and testing workflows for Generative AI applications.
• Collaborate with product and engineering teams to translate use cases into practical AI solutions.
• Support deployment, monitoring, troubleshooting, and continuous improvement of production AI applications.Stay updated with developments in LLMs, agentic AI, retrieval techniques, and Generative AI frameworks.

Job description

About the role

We are looking for a Generative AI Engineer with 2–4 years of experience in AI application development who is passionate about building intelligent applications using Large Language Models, foundation models, and modern Generative AI technologies.

You will work closely with our AI, engineering, and product teams to develop LLM-powered applications, implement retrieval and reasoning workflows, evaluate model performance, and deliver reliable AI solutions for real-world use cases.

The role provides exposure to RAG, AI agents, prompt engineering, LLM evaluation, semantic search, conversational AI, multimodal models, and production-grade Generative AI applications.

Responsibilities

• Design, develop, and deploy Generative AI applications using modern LLMs and AI frameworks.
• Build LLM-powered applications for tasks such as information retrieval, content generation, summarization, and intelligent automation.
• Develop RAG pipelines using document ingestion, chunking, embeddings, retrieval, and reranking techniques.
• Build AI agents that use tools, interact with APIs, and execute multi-step workflows.
• Design, test, and optimize prompts, system instructions, structured outputs, and tool-calling strategies.
• Integrate foundation models and AI services into backend applications and business workflows.
• Implement context management, conversation memory, and knowledge retrieval where required.
• Evaluate LLM outputs for accuracy, relevance, groundedness, consistency, and task completion.
• Investigate hallucinations, retrieval failures, prompt weaknesses, and unexpected model behavior.
• Optimize inference latency, token usage, response quality, and operational costs.
• Implement appropriate validation, guardrails, and fallback mechanisms to improve AI reliability.
• Develop automated evaluation and testing workflows for Generative AI applications.
• Collaborate with product and engineering teams to translate use cases into practical AI solutions.
• Support deployment, monitoring, troubleshooting, and continuous improvement of production AI applications.Stay updated with developments in LLMs, agentic AI, retrieval techniques, and Generative AI frameworks.

Required Skills

• Strong programming skills in Python.
• Practical experience developing AI-powered applications using LLMs or Generative AI technologies.
• Understanding of LLM APIs, prompt engineering, and structured output generation.
• Experience working with REST APIs and integrating AI services into applications.
• Knowledge of embeddings, vector search, and Retrieval-Augmented Generation.
• Understanding of document processing, text chunking, retrieval strategies, and context management.
• Familiarity with databases and data processing.
• Understanding of AI evaluation concepts, including response quality, latency, reliability, and cost.
• Familiarity with Git, software testing, debugging, and version control.
• Ability to investigate model failures and improve application behavior systematically.
• Strong analytical and problem‑solving skills.
• Ability to work collaboratively with AI, engineering, and product teams.

Good to Have

• Experience with OpenAI, Anthropic Claude, Google Gemini, or open-source models available through Hugging Face.
• Hands‑on experience with LangChain, LangGraph, LlamaIndex, or similar frameworks.
• Experience building agentic workflows, tool‑using agents, or multi‑agent applications.
• Familiarity with vector databases such as Pinecone, Qdrant, Weaviate, FAISS, or Chroma.
• Experience with reranking models, hybrid search, and advanced retrieval techniques.
• Exposure to fine‑tuning, model adaptation, or parameter‑efficient fine‑tuning techniques.
• Familiarity with evaluation frameworks such as Ragas, DeepEval, or similar tools.
• Experience developing conversational AI, chatbots, or multimodal AI applications.
• Knowledge of FastAPI, Docker, and cloud deployment platforms.
• Familiarity with LLM observability, tracing, monitoring, and cost optimization.
• Experience deploying and maintaining Generative AI applications in production.

Education

• Bachelor's degree in Computer Science, Information Technology, Artificial Intelligence, Machine Learning, or a related field.
• Candidates with 2–4 years of relevant software or AI development experience and hands‑on Generative AI projects are encouraged to apply.

What We're Looking For

• Strong programming fundamentals and practical experience building LLM-powered applications.
• Genuine interest in exploring Generative AI techniques and emerging model capabilities.
• Ability to turn experimental AI concepts into reliable, useful applications.
• A systematic approach to prompt testing, retrieval evaluation, and model output analysis.
• Understanding of the trade‑offs between model quality, latency, cost, and reliability.
• Ability to debug complex AI workflows and improve application performance.
• Willingness to experiment with different models, frameworks, and architectural approaches.
• Strong communication and collaboration skills.
• A focus on delivering practical AI solutions rather than relying solely on prototypes.
• Hands‑on Generative AI projects and demonstrated implementation skills are highly valued.