Job
Description
About Us: Soul AI is a pioneering company founded by IIT Bombay and IIM Ahmedabad alumni, with a strong founding team from IITs, NITs, and BITS. We specialize in delivering high-quality human-curated data and AI-first scaled operations services. Based in San Francisco and Hyderabad, we are a fast-moving team on a mission to build AI for Good, driving innovation and societal impact. Role Overview: We’re looking for a Generative AI Engineer to join our client’s team and build intelligent systems powered by large language models and other generative AI architectures. This role involves developing and deploying LLM-based features, integrating vector search, fine-tuning models, and collaborating with product and engineering teams to ship robust, scalable GenAI applications. You’ll work across the GenAI stack — from prompt design to inference optimization — and shape how generative models are used in real-world products. Responsibilities: Fine-tune and deploy LLMs (e.g., GPT, LLaMA, Mistral) using frameworks like Hugging Face Transformers or LangChain Build and optimize Retrieval-Augmented Generation (RAG) pipelines using vector databases (e.g., Pinecone, FAISS) Engineer prompts for structured, reliable outputs across use cases (chatbots, summarization, coding copilots, etc.) Implement scalable inference pipelines and optimize latency, throughput, and cost using techniques like quantization or model distillation Collaborate with product, design, and frontend teams to integrate GenAI into user-facing features Monitor, evaluate, and continuously improve model performance, safety, and accuracy in production Ensure compliance with privacy, safety, and responsible AI practices (e.g., content filtering, output sanitization) Required Skills: Strong programming skills in Python, with familiarity in modern ML tooling Practical experience with LLM frameworks (e.g., Hugging Face Transformers, LangChain, LlamaIndex) Experience building or deploying RAG pipelines, including handling embeddings and vector search Understanding of transformer models, prompt engineering, and tokenization strategies Hands-on with APIs (OpenAI, Anthropic, Cohere, etc.) and model serving (FastAPI, Flask, etc.) Experience deploying ML models using Docker, Kubernetes, and/or cloud services (AWS/GCP/Azure) Comfortable with model evaluation, monitoring, and troubleshooting inference pipelines Nice to Have: Experience with multimodal models (e.g., diffusion models, TTS, image/video generation) Knowledge of RLHF, safety alignment, or model fine-tuning best practices Familiarity with open-source LLMs (e.g., Mistral, LLaMA, Falcon, Mixtral) and optimization (LoRA, quantization) Experience with LangChain agents, tool usage, and memory management Contributions to open-source GenAI projects or published demos/blogs on generative AI Exposure to frontend technologies (React/Next.js) for prototyping GenAI tools Educational Qualifications: Bachelor's or Master’s degree in Computer Science, Artificial Intelligence, Machine Learning, Data Science, or a related technical field Candidates with relevant project experience or open-source contributions may be considered regardless of formal degree Show more Show less
