AI Engineer (GenAI Applications)

ABOUT THE ROLEWe are seeking a skilled AI Engineer with 2–3 years of experience to join our dynamic team. The ideal candidate has hands-on experience building applications powered by Generative AI — primarily by integrating existing foundation models via APIs and fine-tuning lightweight open-source models for specific use cases, rather than training models from scratch. You will collaborate with cross-functional teams to develop and deploy AI-powered features that enhance our product offerings.KEY RESPONSIBILITIES• Design and build AI-powered features using existing GenAI models (OpenAI, Anthropic, Gemini, etc.) via their APIs for text, image, and multimodal tasks.• Fine-tune or adapt lightweight open-source models (e.g., using LoRA/QLoRA, PEFT) for domain-specific use cases when off-the-shelf models fall short.• Build robust prompt engineering pipelines, including prompt design, evaluation, and iteration for consistent, reliable outputs.• Implement RAG (Retrieval-Augmented Generation) pipelines using vector databases (pgvector, Pinecone, Weaviate, etc.) to ground model outputs in proprietary data.• Design and orchestrate multi-step AI workflows/agents (tool use, function calling, chaining) for complex tasks.• Manage the end-to-end lifecycle of AI features: data preparation, model/API selection, evaluation, integration, and deployment.• Collaborate with backend/frontend engineers and product managers to integrate AI capabilities into existing systems and products.• Monitor and optimize model performance, latency, and cost (token usage, API costs, inference costs for self-hosted models).• Stay current with the fast-evolving GenAI landscape (new model releases, APIs, techniques) and evaluate their applicability to our product.• Ensure ethical AI practices — fairness, transparency, data privacy, and responsible handling of user data sent to third-party model APIs.REQUIRED QUALIFICATIONS• Bachelor's or Master's degree in Computer Science, AI/ML, or a related field (or equivalent practical experience).• 2–3 years of hands-on experience building applications using GenAI/LLM APIs (OpenAI, Anthropic, Google, etc.).• Strong Python skills, with experience calling and orchestrating AI APIs in production systems.• Practical experience with prompt engineering, structured outputs, and function/tool calling.• Experience fine-tuning or adapting pre-trained/open-source models (Hugging Face ecosystem, LoRA/QLoRA/PEFT) for specific tasks.• Experience building RAG pipelines — embeddings, vector search, chunking strategies, retrieval evaluation.• Familiarity with agent frameworks/orchestration (LangChain, LangGraph, LlamaIndex, or similar).• Understanding of transformer architecture fundamentals — enough to reason about model behavior, limitations, and fine-tuning trade-offs (deep training-from-scratch expertise not required).iSummation Technologies Pvt Ltd • Experience with cloud platforms (AWS, GCP, Azure) for hosting lightweight models and APIbased services.• Strong problem-solving skills and ability to work collaboratively in a fast-moving environment.PREFERRED SKILLS• Experience with model evaluation frameworks (e.g., LangSmith, Ragas, custom eval harnesses) for measuring GenAI output quality.• Familiarity with MLOps/LLMOps practices — versioning prompts, monitoring model drift, cost tracking, CI/CD for AI features.• Experience with computer vision APIs/models (OCR, image generation/editing APIs, visionlanguage models) for multimodal use cases.• Knowledge of responsible AI practices — bias mitigation, hallucination detection, guardrails, and content moderation for GenAI outputs.• Experience with self-hosted inference (vLLM, Ollama, or similar) for lightweight fine-tuned models.Experience: 4+ yearsExperience Preferred: Build applications using GenAI/LLM APIs & Strong Python skillsLocation: Bodakdev, Ahmedabad (WFO)Company Profile: https://www.isummation.com/