We are looking for a forward-thinking and skilled Generative AI Engineer to join our [Engineering / AI Innovation] team. In this role, you will be at the forefront of building cutting-edge, LLM-powered applications, intelligent automation agents, and scalable retrieval systems. You will bridge the gap between advanced machine learning research and robust software engineering, transforming complex business challenges into production-grade generative AI products.

Key Responsibilities

- LLM Integration &
- Application Development:

Design, build, and deploy production-grade applications integrating large language models (LLMs) via APIs from major providers (OpenAI, Anthropic, open-source models via Hugging Face/Ollama).

- RAG Architecture &

- Vector Engineering:

Implement advanced Retrieval-Augmented Generation (RAG) pipelines, semantic search layers, and chunking strategies utilizing vector databases (e.g., Pinecone, Milvus, Qdrant, FAISS).

- Agentic Workflows: Develop multi-agent frameworks, automated reasoning loops, and autonomous workflows using tools like LangChain, LlamaIndex, or Semantic Kernel.

- Fine-Tuning &

- Model Evaluation:

Fine-tune open-source foundational models (e.g., Llama, Mistral) for domain-specific tasks. Establish automated evaluation benchmarks, scoring frameworks (e.g., Ragas, TruLens), and guardrails for safety and hallucination reduction.

- MLOps &

- Production Deployment:

Optimize inference performance, token latency, and cost. Deploy scalable, containerized AI solutions on cloud platforms (AWS/Azure/GCP) using Docker, Kubernetes, and serverless architectures.

- Cross-Functional Collaboration: Work closely with product managers, data scientists, and frontend/backend engineers to translate business requirements into technical AI roadmaps.





Key Skills &

- Qualifications

- Software Engineering Core: Strong proficiency in Python (minimum 3+ years) and standard software development practices (OOP, modular design, asynchronous programming, clean code, Git version control).

- Gen AI Ecosystem: Hands-on experience with LLM orchestration frameworks (LangChain, LlamaIndex, Semantic Kernel) and prompt engineering patterns.

- Data &
- Vector Systems:

Solid understanding of data pipelines, embeddings, and working experience with vector databases.

- Web &

- API Frameworks:

Experience building backend services and APIs using FastAPI or Flask.

- Cloud &

- Infrastructure:

Familiarity with cloud-native development patterns, CI/CD pipelines, and deploying containerized applications on AWS, Azure, or GCP.

- Analytical Mindset: Strong problem-solving skills with a deep understanding of trade-offs between model size, cost, accuracy, and latency.

Preferred / Nice-to-Have Skills

- Experience with fine-tuning techniques (LoRA, QLoRA) and RLHF (Reinforcement Learning from Human Feedback).

- Background in evaluating LLM security vulnerabilities, prompt injection defenses, and enterprise data privacy compliance.

- Contributions to open-source AI projects or a strong portfolio of deployed generative AI apps.

- Degree in Computer Science, Artificial Intelligence, Data Science, or a related quantitative field.

What We Offer

- Market-competitive salary and performance bonus structure.

- Flexible working hours and hybrid/remote work culture.

- Continuous learning budget for certifications, conferences, and courses.

- Opportunity to work with cutting-edge AI technology that directly impacts our core products and users.

Pay: ₹50,000.00 - ₹90,000.00 per month

Work Location: In person

📌 Generative AI (Gen AI) Engineer (Bhandup)
🏢 Nelson Infotech
📍 Bhandup